vllm-cpu-avx512vnni 0.10.2.post2__cp312-cp312-manylinux_2_17_x86_64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of vllm-cpu-avx512vnni might be problematic. Click here for more details.
- vllm/_C.abi3.so +0 -0
- vllm/__init__.py +220 -0
- vllm/_bc_linter.py +59 -0
- vllm/_custom_ops.py +2022 -0
- vllm/_ipex_ops.py +404 -0
- vllm/_version.py +34 -0
- vllm/adapter_commons/__init__.py +0 -0
- vllm/adapter_commons/layers.py +16 -0
- vllm/adapter_commons/models.py +106 -0
- vllm/adapter_commons/request.py +26 -0
- vllm/adapter_commons/utils.py +93 -0
- vllm/adapter_commons/worker_manager.py +39 -0
- vllm/assets/__init__.py +0 -0
- vllm/assets/audio.py +45 -0
- vllm/assets/base.py +41 -0
- vllm/assets/image.py +50 -0
- vllm/assets/video.py +138 -0
- vllm/attention/__init__.py +19 -0
- vllm/attention/backends/__init__.py +0 -0
- vllm/attention/backends/abstract.py +348 -0
- vllm/attention/backends/differential_flash_attn.py +935 -0
- vllm/attention/backends/dual_chunk_flash_attn.py +1499 -0
- vllm/attention/backends/flash_attn.py +933 -0
- vllm/attention/backends/flashmla.py +238 -0
- vllm/attention/backends/mla/__init__.py +0 -0
- vllm/attention/backends/mla/common.py +1310 -0
- vllm/attention/backends/placeholder_attn.py +340 -0
- vllm/attention/backends/rocm_aiter_mla.py +410 -0
- vllm/attention/backends/rocm_flash_attn.py +953 -0
- vllm/attention/backends/triton_mla.py +111 -0
- vllm/attention/backends/utils.py +610 -0
- vllm/attention/backends/xformers.py +805 -0
- vllm/attention/layer.py +552 -0
- vllm/attention/layers/__init__.py +0 -0
- vllm/attention/layers/chunked_local_attention.py +91 -0
- vllm/attention/layers/cross_attention.py +159 -0
- vllm/attention/layers/encoder_only_attention.py +86 -0
- vllm/attention/ops/__init__.py +0 -0
- vllm/attention/ops/chunked_prefill_paged_decode.py +405 -0
- vllm/attention/ops/common.py +139 -0
- vllm/attention/ops/flashmla.py +123 -0
- vllm/attention/ops/merge_attn_states.py +43 -0
- vllm/attention/ops/paged_attn.py +261 -0
- vllm/attention/ops/pallas_kv_cache_update.py +124 -0
- vllm/attention/ops/prefix_prefill.py +928 -0
- vllm/attention/ops/rocm_aiter_mla.py +104 -0
- vllm/attention/ops/rocm_aiter_paged_attn.py +102 -0
- vllm/attention/ops/triton_decode_attention.py +676 -0
- vllm/attention/ops/triton_flash_attention.py +984 -0
- vllm/attention/ops/triton_merge_attn_states.py +97 -0
- vllm/attention/ops/triton_unified_attention.py +854 -0
- vllm/attention/selector.py +243 -0
- vllm/attention/utils/__init__.py +0 -0
- vllm/attention/utils/fa_utils.py +85 -0
- vllm/attention/utils/kv_sharing_utils.py +33 -0
- vllm/beam_search.py +87 -0
- vllm/benchmarks/__init__.py +0 -0
- vllm/benchmarks/datasets.py +2651 -0
- vllm/benchmarks/latency.py +170 -0
- vllm/benchmarks/lib/__init__.py +3 -0
- vllm/benchmarks/lib/endpoint_request_func.py +510 -0
- vllm/benchmarks/lib/ready_checker.py +72 -0
- vllm/benchmarks/lib/utils.py +80 -0
- vllm/benchmarks/serve.py +1247 -0
- vllm/benchmarks/throughput.py +696 -0
- vllm/collect_env.py +823 -0
- vllm/compilation/__init__.py +0 -0
- vllm/compilation/activation_quant_fusion.py +193 -0
- vllm/compilation/backends.py +641 -0
- vllm/compilation/base_static_graph.py +51 -0
- vllm/compilation/collective_fusion.py +1190 -0
- vllm/compilation/compiler_interface.py +572 -0
- vllm/compilation/counter.py +47 -0
- vllm/compilation/cuda_graph.py +193 -0
- vllm/compilation/cuda_piecewise_backend.py +117 -0
- vllm/compilation/decorators.py +316 -0
- vllm/compilation/fix_functionalization.py +208 -0
- vllm/compilation/fusion.py +600 -0
- vllm/compilation/fusion_attn.py +303 -0
- vllm/compilation/fx_utils.py +84 -0
- vllm/compilation/inductor_pass.py +136 -0
- vllm/compilation/monitor.py +57 -0
- vllm/compilation/multi_output_match.py +109 -0
- vllm/compilation/noop_elimination.py +165 -0
- vllm/compilation/pass_manager.py +88 -0
- vllm/compilation/sequence_parallelism.py +484 -0
- vllm/compilation/torch25_custom_graph_pass.py +42 -0
- vllm/compilation/vllm_inductor_pass.py +50 -0
- vllm/compilation/wrapper.py +138 -0
- vllm/config/__init__.py +3921 -0
- vllm/config/cache.py +214 -0
- vllm/config/compilation.py +580 -0
- vllm/config/kv_events.py +50 -0
- vllm/config/kv_transfer.py +111 -0
- vllm/config/load.py +113 -0
- vllm/config/lora.py +132 -0
- vllm/config/parallel.py +446 -0
- vllm/config/scheduler.py +304 -0
- vllm/config/utils.py +29 -0
- vllm/connections.py +174 -0
- vllm/core/__init__.py +0 -0
- vllm/core/block/__init__.py +0 -0
- vllm/core/block/block_table.py +399 -0
- vllm/core/block/common.py +371 -0
- vllm/core/block/cpu_gpu_block_allocator.py +439 -0
- vllm/core/block/interfaces.py +319 -0
- vllm/core/block/naive_block.py +466 -0
- vllm/core/block/prefix_caching_block.py +1135 -0
- vllm/core/block/utils.py +28 -0
- vllm/core/block_manager.py +523 -0
- vllm/core/evictor.py +157 -0
- vllm/core/interfaces.py +139 -0
- vllm/core/placeholder_block_space_manager.py +103 -0
- vllm/core/scheduler.py +2028 -0
- vllm/device_allocator/__init__.py +0 -0
- vllm/device_allocator/cumem.py +286 -0
- vllm/distributed/__init__.py +6 -0
- vllm/distributed/communication_op.py +41 -0
- vllm/distributed/device_communicators/__init__.py +0 -0
- vllm/distributed/device_communicators/all2all.py +259 -0
- vllm/distributed/device_communicators/all_reduce_utils.py +292 -0
- vllm/distributed/device_communicators/base_device_communicator.py +277 -0
- vllm/distributed/device_communicators/cpu_communicator.py +201 -0
- vllm/distributed/device_communicators/cuda_communicator.py +294 -0
- vllm/distributed/device_communicators/cuda_wrapper.py +180 -0
- vllm/distributed/device_communicators/custom_all_reduce.py +311 -0
- vllm/distributed/device_communicators/pynccl.py +290 -0
- vllm/distributed/device_communicators/pynccl_wrapper.py +382 -0
- vllm/distributed/device_communicators/quick_all_reduce.py +278 -0
- vllm/distributed/device_communicators/ray_communicator.py +258 -0
- vllm/distributed/device_communicators/shm_broadcast.py +585 -0
- vllm/distributed/device_communicators/symm_mem.py +136 -0
- vllm/distributed/device_communicators/tpu_communicator.py +102 -0
- vllm/distributed/device_communicators/xpu_communicator.py +69 -0
- vllm/distributed/eplb/__init__.py +8 -0
- vllm/distributed/eplb/eplb_state.py +619 -0
- vllm/distributed/eplb/rebalance_algo.py +234 -0
- vllm/distributed/eplb/rebalance_execute.py +424 -0
- vllm/distributed/kv_events.py +362 -0
- vllm/distributed/kv_transfer/README.md +29 -0
- vllm/distributed/kv_transfer/__init__.py +13 -0
- vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg +0 -0
- vllm/distributed/kv_transfer/kv_connector/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_connector/base.py +10 -0
- vllm/distributed/kv_transfer/kv_connector/factory.py +108 -0
- vllm/distributed/kv_transfer/kv_connector/utils.py +246 -0
- vllm/distributed/kv_transfer/kv_connector/v1/__init__.py +6 -0
- vllm/distributed/kv_transfer/kv_connector/v1/base.py +356 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py +167 -0
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +266 -0
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +1319 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py +484 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py +542 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py +266 -0
- vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py +414 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/base.py +175 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py +161 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py +237 -0
- vllm/distributed/kv_transfer/kv_pipe/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_pipe/base.py +67 -0
- vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py +290 -0
- vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py +280 -0
- vllm/distributed/kv_transfer/kv_transfer_state.py +73 -0
- vllm/distributed/parallel_state.py +1489 -0
- vllm/distributed/tpu_distributed_utils.py +178 -0
- vllm/distributed/utils.py +536 -0
- vllm/engine/__init__.py +0 -0
- vllm/engine/arg_utils.py +1857 -0
- vllm/engine/async_llm_engine.py +1044 -0
- vllm/engine/async_timeout.py +173 -0
- vllm/engine/llm_engine.py +1849 -0
- vllm/engine/metrics.py +577 -0
- vllm/engine/metrics_types.py +84 -0
- vllm/engine/multiprocessing/__init__.py +145 -0
- vllm/engine/multiprocessing/client.py +643 -0
- vllm/engine/multiprocessing/engine.py +470 -0
- vllm/engine/output_processor/__init__.py +0 -0
- vllm/engine/output_processor/interfaces.py +61 -0
- vllm/engine/output_processor/single_step.py +145 -0
- vllm/engine/output_processor/stop_checker.py +131 -0
- vllm/engine/output_processor/util.py +28 -0
- vllm/engine/protocol.py +343 -0
- vllm/entrypoints/__init__.py +0 -0
- vllm/entrypoints/api_server.py +178 -0
- vllm/entrypoints/chat_utils.py +1535 -0
- vllm/entrypoints/cli/__init__.py +12 -0
- vllm/entrypoints/cli/benchmark/__init__.py +0 -0
- vllm/entrypoints/cli/benchmark/base.py +25 -0
- vllm/entrypoints/cli/benchmark/latency.py +21 -0
- vllm/entrypoints/cli/benchmark/main.py +58 -0
- vllm/entrypoints/cli/benchmark/serve.py +21 -0
- vllm/entrypoints/cli/benchmark/throughput.py +21 -0
- vllm/entrypoints/cli/collect_env.py +36 -0
- vllm/entrypoints/cli/main.py +60 -0
- vllm/entrypoints/cli/openai.py +214 -0
- vllm/entrypoints/cli/run_batch.py +69 -0
- vllm/entrypoints/cli/serve.py +232 -0
- vllm/entrypoints/cli/types.py +29 -0
- vllm/entrypoints/constants.py +10 -0
- vllm/entrypoints/context.py +444 -0
- vllm/entrypoints/harmony_utils.py +431 -0
- vllm/entrypoints/launcher.py +168 -0
- vllm/entrypoints/llm.py +1579 -0
- vllm/entrypoints/logger.py +79 -0
- vllm/entrypoints/openai/__init__.py +0 -0
- vllm/entrypoints/openai/api_server.py +2011 -0
- vllm/entrypoints/openai/cli_args.py +281 -0
- vllm/entrypoints/openai/logits_processors.py +90 -0
- vllm/entrypoints/openai/protocol.py +2590 -0
- vllm/entrypoints/openai/run_batch.py +497 -0
- vllm/entrypoints/openai/serving_chat.py +1591 -0
- vllm/entrypoints/openai/serving_classification.py +176 -0
- vllm/entrypoints/openai/serving_completion.py +688 -0
- vllm/entrypoints/openai/serving_embedding.py +632 -0
- vllm/entrypoints/openai/serving_engine.py +996 -0
- vllm/entrypoints/openai/serving_models.py +288 -0
- vllm/entrypoints/openai/serving_pooling.py +277 -0
- vllm/entrypoints/openai/serving_responses.py +1690 -0
- vllm/entrypoints/openai/serving_score.py +479 -0
- vllm/entrypoints/openai/serving_tokenization.py +196 -0
- vllm/entrypoints/openai/serving_transcription.py +136 -0
- vllm/entrypoints/openai/speech_to_text.py +388 -0
- vllm/entrypoints/openai/tool_parsers/__init__.py +51 -0
- vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py +164 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py +367 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py +370 -0
- vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py +185 -0
- vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py +259 -0
- vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py +237 -0
- vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py +418 -0
- vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py +372 -0
- vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py +216 -0
- vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py +308 -0
- vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py +377 -0
- vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py +316 -0
- vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py +269 -0
- vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py +816 -0
- vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py +369 -0
- vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py +73 -0
- vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py +112 -0
- vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py +308 -0
- vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py +707 -0
- vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py +679 -0
- vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py +296 -0
- vllm/entrypoints/openai/tool_parsers/utils.py +124 -0
- vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py +524 -0
- vllm/entrypoints/renderer.py +395 -0
- vllm/entrypoints/score_utils.py +232 -0
- vllm/entrypoints/ssl.py +75 -0
- vllm/entrypoints/tool.py +139 -0
- vllm/entrypoints/tool_server.py +195 -0
- vllm/entrypoints/utils.py +328 -0
- vllm/env_override.py +23 -0
- vllm/envs.py +1354 -0
- vllm/executor/__init__.py +0 -0
- vllm/executor/executor_base.py +378 -0
- vllm/executor/mp_distributed_executor.py +244 -0
- vllm/executor/msgspec_utils.py +35 -0
- vllm/executor/multiproc_worker_utils.py +279 -0
- vllm/executor/ray_distributed_executor.py +699 -0
- vllm/executor/ray_utils.py +410 -0
- vllm/executor/uniproc_executor.py +152 -0
- vllm/forward_context.py +273 -0
- vllm/inputs/__init__.py +44 -0
- vllm/inputs/data.py +356 -0
- vllm/inputs/parse.py +151 -0
- vllm/inputs/preprocess.py +973 -0
- vllm/inputs/registry.py +251 -0
- vllm/logger.py +229 -0
- vllm/logging_utils/__init__.py +8 -0
- vllm/logging_utils/dump_input.py +81 -0
- vllm/logging_utils/formatter.py +79 -0
- vllm/logits_process.py +119 -0
- vllm/logprobs.py +28 -0
- vllm/lora/__init__.py +0 -0
- vllm/lora/layers/__init__.py +34 -0
- vllm/lora/layers/base.py +69 -0
- vllm/lora/layers/base_linear.py +184 -0
- vllm/lora/layers/column_parallel_linear.py +622 -0
- vllm/lora/layers/logits_processor.py +247 -0
- vllm/lora/layers/qkv_x_parallel_linear.py +8 -0
- vllm/lora/layers/replicated_linear.py +61 -0
- vllm/lora/layers/row_parallel_linear.py +201 -0
- vllm/lora/layers/utils.py +60 -0
- vllm/lora/layers/vocal_parallel_embedding.py +172 -0
- vllm/lora/lora.py +199 -0
- vllm/lora/models.py +792 -0
- vllm/lora/ops/__init__.py +0 -0
- vllm/lora/ops/ipex_ops/__init__.py +7 -0
- vllm/lora/ops/ipex_ops/lora_ops.py +44 -0
- vllm/lora/ops/torch_ops/__init__.py +16 -0
- vllm/lora/ops/torch_ops/lora_ops.py +119 -0
- vllm/lora/ops/triton_ops/__init__.py +12 -0
- vllm/lora/ops/triton_ops/kernel_utils.py +243 -0
- vllm/lora/ops/triton_ops/lora_expand_op.py +291 -0
- vllm/lora/ops/triton_ops/lora_kernel_metadata.py +148 -0
- vllm/lora/ops/triton_ops/lora_shrink_op.py +245 -0
- vllm/lora/ops/triton_ops/utils.py +126 -0
- vllm/lora/ops/xla_ops/__init__.py +7 -0
- vllm/lora/ops/xla_ops/lora_ops.py +145 -0
- vllm/lora/peft_helper.py +127 -0
- vllm/lora/punica_wrapper/__init__.py +10 -0
- vllm/lora/punica_wrapper/punica_base.py +458 -0
- vllm/lora/punica_wrapper/punica_cpu.py +349 -0
- vllm/lora/punica_wrapper/punica_gpu.py +279 -0
- vllm/lora/punica_wrapper/punica_selector.py +20 -0
- vllm/lora/punica_wrapper/punica_tpu.py +391 -0
- vllm/lora/punica_wrapper/punica_xpu.py +276 -0
- vllm/lora/punica_wrapper/utils.py +136 -0
- vllm/lora/request.py +99 -0
- vllm/lora/resolver.py +85 -0
- vllm/lora/utils.py +246 -0
- vllm/lora/worker_manager.py +256 -0
- vllm/model_executor/__init__.py +16 -0
- vllm/model_executor/custom_op.py +194 -0
- vllm/model_executor/layers/__init__.py +0 -0
- vllm/model_executor/layers/activation.py +575 -0
- vllm/model_executor/layers/attention_layer_base.py +23 -0
- vllm/model_executor/layers/fla/__init__.py +8 -0
- vllm/model_executor/layers/fla/ops/__init__.py +17 -0
- vllm/model_executor/layers/fla/ops/chunk.py +225 -0
- vllm/model_executor/layers/fla/ops/chunk_delta_h.py +290 -0
- vllm/model_executor/layers/fla/ops/chunk_o.py +177 -0
- vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py +140 -0
- vllm/model_executor/layers/fla/ops/cumsum.py +226 -0
- vllm/model_executor/layers/fla/ops/fused_recurrent.py +366 -0
- vllm/model_executor/layers/fla/ops/index.py +39 -0
- vllm/model_executor/layers/fla/ops/l2norm.py +143 -0
- vllm/model_executor/layers/fla/ops/layernorm_guard.py +337 -0
- vllm/model_executor/layers/fla/ops/op.py +39 -0
- vllm/model_executor/layers/fla/ops/solve_tril.py +365 -0
- vllm/model_executor/layers/fla/ops/utils.py +180 -0
- vllm/model_executor/layers/fla/ops/wy_fast.py +114 -0
- vllm/model_executor/layers/fused_moe/__init__.py +80 -0
- vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +304 -0
- vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py +164 -0
- vllm/model_executor/layers/fused_moe/config.py +497 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +122 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +114 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +138 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +154 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json +173 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/README +12 -0
- vllm/model_executor/layers/fused_moe/cpu_fused_moe.py +297 -0
- vllm/model_executor/layers/fused_moe/cutlass_moe.py +996 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +370 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_utils.py +413 -0
- vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +280 -0
- vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +229 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py +243 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py +97 -0
- vllm/model_executor/layers/fused_moe/fused_batched_moe.py +1042 -0
- vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +240 -0
- vllm/model_executor/layers/fused_moe/fused_moe.py +2081 -0
- vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py +247 -0
- vllm/model_executor/layers/fused_moe/layer.py +1951 -0
- vllm/model_executor/layers/fused_moe/modular_kernel.py +892 -0
- vllm/model_executor/layers/fused_moe/moe_align_block_size.py +87 -0
- vllm/model_executor/layers/fused_moe/moe_pallas.py +80 -0
- vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py +205 -0
- vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +60 -0
- vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py +321 -0
- vllm/model_executor/layers/fused_moe/prepare_finalize.py +72 -0
- vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +431 -0
- vllm/model_executor/layers/fused_moe/routing_simulator.py +291 -0
- vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py +146 -0
- vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +171 -0
- vllm/model_executor/layers/fused_moe/trtllm_moe.py +197 -0
- vllm/model_executor/layers/fused_moe/utils.py +270 -0
- vllm/model_executor/layers/layernorm.py +381 -0
- vllm/model_executor/layers/lightning_attn.py +661 -0
- vllm/model_executor/layers/linear.py +1567 -0
- vllm/model_executor/layers/logits_processor.py +199 -0
- vllm/model_executor/layers/mamba/__init__.py +0 -0
- vllm/model_executor/layers/mamba/abstract.py +45 -0
- vllm/model_executor/layers/mamba/linear_attn.py +432 -0
- vllm/model_executor/layers/mamba/mamba2_metadata.py +186 -0
- vllm/model_executor/layers/mamba/mamba_mixer.py +517 -0
- vllm/model_executor/layers/mamba/mamba_mixer2.py +803 -0
- vllm/model_executor/layers/mamba/mamba_utils.py +202 -0
- vllm/model_executor/layers/mamba/ops/__init__.py +0 -0
- vllm/model_executor/layers/mamba/ops/causal_conv1d.py +982 -0
- vllm/model_executor/layers/mamba/ops/layernorm_gated.py +168 -0
- vllm/model_executor/layers/mamba/ops/mamba_ssm.py +414 -0
- vllm/model_executor/layers/mamba/ops/ssd_bmm.py +262 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py +574 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py +751 -0
- vllm/model_executor/layers/mamba/ops/ssd_combined.py +248 -0
- vllm/model_executor/layers/mamba/ops/ssd_state_passing.py +248 -0
- vllm/model_executor/layers/mamba/short_conv.py +270 -0
- vllm/model_executor/layers/mla.py +158 -0
- vllm/model_executor/layers/pooler.py +732 -0
- vllm/model_executor/layers/quantization/__init__.py +157 -0
- vllm/model_executor/layers/quantization/auto_round.py +388 -0
- vllm/model_executor/layers/quantization/awq.py +228 -0
- vllm/model_executor/layers/quantization/awq_marlin.py +548 -0
- vllm/model_executor/layers/quantization/awq_triton.py +320 -0
- vllm/model_executor/layers/quantization/base_config.py +164 -0
- vllm/model_executor/layers/quantization/bitblas.py +464 -0
- vllm/model_executor/layers/quantization/bitsandbytes.py +621 -0
- vllm/model_executor/layers/quantization/compressed_tensors/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +795 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +1651 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +27 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +366 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +55 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py +160 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py +105 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +161 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py +169 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py +135 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +121 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +156 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +111 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +201 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py +227 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py +135 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py +21 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py +13 -0
- vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py +206 -0
- vllm/model_executor/layers/quantization/compressed_tensors/utils.py +216 -0
- vllm/model_executor/layers/quantization/deepgemm.py +81 -0
- vllm/model_executor/layers/quantization/deepspeedfp.py +196 -0
- vllm/model_executor/layers/quantization/experts_int8.py +215 -0
- vllm/model_executor/layers/quantization/fbgemm_fp8.py +172 -0
- vllm/model_executor/layers/quantization/fp8.py +1179 -0
- vllm/model_executor/layers/quantization/gguf.py +597 -0
- vllm/model_executor/layers/quantization/gptq.py +300 -0
- vllm/model_executor/layers/quantization/gptq_bitblas.py +448 -0
- vllm/model_executor/layers/quantization/gptq_marlin.py +700 -0
- vllm/model_executor/layers/quantization/gptq_marlin_24.py +297 -0
- vllm/model_executor/layers/quantization/hqq_marlin.py +333 -0
- vllm/model_executor/layers/quantization/inc.py +61 -0
- vllm/model_executor/layers/quantization/input_quant_fp8.py +103 -0
- vllm/model_executor/layers/quantization/ipex_quant.py +410 -0
- vllm/model_executor/layers/quantization/kernels/__init__.py +0 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +91 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +93 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py +116 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py +302 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py +92 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py +117 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py +92 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +143 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +144 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +139 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +67 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +89 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py +163 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py +206 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py +137 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py +41 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py +104 -0
- vllm/model_executor/layers/quantization/kv_cache.py +139 -0
- vllm/model_executor/layers/quantization/modelopt.py +1548 -0
- vllm/model_executor/layers/quantization/moe_wna16.py +473 -0
- vllm/model_executor/layers/quantization/mxfp4.py +951 -0
- vllm/model_executor/layers/quantization/petit.py +306 -0
- vllm/model_executor/layers/quantization/ptpc_fp8.py +129 -0
- vllm/model_executor/layers/quantization/quark/__init__.py +0 -0
- vllm/model_executor/layers/quantization/quark/quark.py +431 -0
- vllm/model_executor/layers/quantization/quark/quark_moe.py +434 -0
- vllm/model_executor/layers/quantization/quark/schemes/__init__.py +9 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py +55 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +112 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +163 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +122 -0
- vllm/model_executor/layers/quantization/quark/utils.py +105 -0
- vllm/model_executor/layers/quantization/rtn.py +456 -0
- vllm/model_executor/layers/quantization/schema.py +86 -0
- vllm/model_executor/layers/quantization/torchao.py +214 -0
- vllm/model_executor/layers/quantization/tpu_int8.py +125 -0
- vllm/model_executor/layers/quantization/utils/__init__.py +6 -0
- vllm/model_executor/layers/quantization/utils/allspark_utils.py +52 -0
- vllm/model_executor/layers/quantization/utils/bitblas_utils.py +210 -0
- vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +18 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/README.md +3 -0
- vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py +85 -0
- vllm/model_executor/layers/quantization/utils/flashinfer_utils.py +258 -0
- vllm/model_executor/layers/quantization/utils/fp8_utils.py +795 -0
- vllm/model_executor/layers/quantization/utils/gptq_utils.py +96 -0
- vllm/model_executor/layers/quantization/utils/int8_utils.py +492 -0
- vllm/model_executor/layers/quantization/utils/layer_utils.py +40 -0
- vllm/model_executor/layers/quantization/utils/machete_utils.py +50 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils.py +479 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py +396 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +345 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test.py +165 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py +464 -0
- vllm/model_executor/layers/quantization/utils/mxfp4_utils.py +132 -0
- vllm/model_executor/layers/quantization/utils/mxfp8_utils.py +20 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py +137 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py +59 -0
- vllm/model_executor/layers/quantization/utils/petit_utils.py +122 -0
- vllm/model_executor/layers/quantization/utils/quant_utils.py +627 -0
- vllm/model_executor/layers/quantization/utils/w8a8_utils.py +458 -0
- vllm/model_executor/layers/resampler.py +270 -0
- vllm/model_executor/layers/rotary_embedding/__init__.py +190 -0
- vllm/model_executor/layers/rotary_embedding/base.py +156 -0
- vllm/model_executor/layers/rotary_embedding/common.py +105 -0
- vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py +140 -0
- vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py +197 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py +41 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py +67 -0
- vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py +80 -0
- vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py +115 -0
- vllm/model_executor/layers/rotary_embedding/llama3_rope.py +54 -0
- vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py +81 -0
- vllm/model_executor/layers/rotary_embedding/mrope.py +1140 -0
- vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py +42 -0
- vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py +129 -0
- vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py +68 -0
- vllm/model_executor/layers/sampler.py +1198 -0
- vllm/model_executor/layers/shared_fused_moe/__init__.py +6 -0
- vllm/model_executor/layers/shared_fused_moe/shared_fused_moe.py +56 -0
- vllm/model_executor/layers/utils.py +196 -0
- vllm/model_executor/layers/vocab_parallel_embedding.py +487 -0
- vllm/model_executor/model_loader/__init__.py +138 -0
- vllm/model_executor/model_loader/base_loader.py +52 -0
- vllm/model_executor/model_loader/bitsandbytes_loader.py +787 -0
- vllm/model_executor/model_loader/default_loader.py +278 -0
- vllm/model_executor/model_loader/dummy_loader.py +28 -0
- vllm/model_executor/model_loader/gguf_loader.py +155 -0
- vllm/model_executor/model_loader/runai_streamer_loader.py +104 -0
- vllm/model_executor/model_loader/sharded_state_loader.py +199 -0
- vllm/model_executor/model_loader/tensorizer.py +743 -0
- vllm/model_executor/model_loader/tensorizer_loader.py +143 -0
- vllm/model_executor/model_loader/tpu.py +114 -0
- vllm/model_executor/model_loader/utils.py +271 -0
- vllm/model_executor/model_loader/weight_utils.py +946 -0
- vllm/model_executor/models/__init__.py +30 -0
- vllm/model_executor/models/adapters.py +542 -0
- vllm/model_executor/models/aimv2.py +246 -0
- vllm/model_executor/models/apertus.py +582 -0
- vllm/model_executor/models/arcee.py +423 -0
- vllm/model_executor/models/arctic.py +560 -0
- vllm/model_executor/models/aria.py +662 -0
- vllm/model_executor/models/aya_vision.py +470 -0
- vllm/model_executor/models/baichuan.py +475 -0
- vllm/model_executor/models/bailing_moe.py +529 -0
- vllm/model_executor/models/bamba.py +582 -0
- vllm/model_executor/models/bart.py +1343 -0
- vllm/model_executor/models/bert.py +613 -0
- vllm/model_executor/models/bert_with_rope.py +687 -0
- vllm/model_executor/models/blip.py +339 -0
- vllm/model_executor/models/blip2.py +716 -0
- vllm/model_executor/models/bloom.py +374 -0
- vllm/model_executor/models/chameleon.py +1141 -0
- vllm/model_executor/models/chatglm.py +479 -0
- vllm/model_executor/models/clip.py +407 -0
- vllm/model_executor/models/cohere2_vision.py +484 -0
- vllm/model_executor/models/commandr.py +467 -0
- vllm/model_executor/models/config.py +434 -0
- vllm/model_executor/models/constant_size_cache.py +137 -0
- vllm/model_executor/models/dbrx.py +473 -0
- vllm/model_executor/models/deepseek.py +491 -0
- vllm/model_executor/models/deepseek_eagle.py +241 -0
- vllm/model_executor/models/deepseek_mtp.py +282 -0
- vllm/model_executor/models/deepseek_v2.py +1058 -0
- vllm/model_executor/models/deepseek_vl2.py +661 -0
- vllm/model_executor/models/donut.py +387 -0
- vllm/model_executor/models/dots1.py +547 -0
- vllm/model_executor/models/ernie45.py +43 -0
- vllm/model_executor/models/ernie45_moe.py +608 -0
- vllm/model_executor/models/ernie45_vl.py +1510 -0
- vllm/model_executor/models/ernie45_vl_moe.py +728 -0
- vllm/model_executor/models/ernie_mtp.py +287 -0
- vllm/model_executor/models/exaone.py +552 -0
- vllm/model_executor/models/exaone4.py +535 -0
- vllm/model_executor/models/fairseq2_llama.py +154 -0
- vllm/model_executor/models/falcon.py +511 -0
- vllm/model_executor/models/falcon_h1.py +739 -0
- vllm/model_executor/models/florence2.py +1107 -0
- vllm/model_executor/models/fuyu.py +401 -0
- vllm/model_executor/models/gemma.py +428 -0
- vllm/model_executor/models/gemma2.py +425 -0
- vllm/model_executor/models/gemma3.py +542 -0
- vllm/model_executor/models/gemma3_mm.py +723 -0
- vllm/model_executor/models/gemma3n.py +830 -0
- vllm/model_executor/models/gemma3n_mm.py +767 -0
- vllm/model_executor/models/glm.py +23 -0
- vllm/model_executor/models/glm4.py +305 -0
- vllm/model_executor/models/glm4_1v.py +1669 -0
- vllm/model_executor/models/glm4_moe.py +703 -0
- vllm/model_executor/models/glm4_moe_mtp.py +306 -0
- vllm/model_executor/models/glm4v.py +654 -0
- vllm/model_executor/models/gpt2.py +383 -0
- vllm/model_executor/models/gpt_bigcode.py +346 -0
- vllm/model_executor/models/gpt_j.py +340 -0
- vllm/model_executor/models/gpt_neox.py +333 -0
- vllm/model_executor/models/gpt_oss.py +687 -0
- vllm/model_executor/models/granite.py +498 -0
- vllm/model_executor/models/granite_speech.py +799 -0
- vllm/model_executor/models/granitemoe.py +541 -0
- vllm/model_executor/models/granitemoehybrid.py +684 -0
- vllm/model_executor/models/granitemoeshared.py +342 -0
- vllm/model_executor/models/gritlm.py +262 -0
- vllm/model_executor/models/grok1.py +550 -0
- vllm/model_executor/models/h2ovl.py +536 -0
- vllm/model_executor/models/hunyuan_v1.py +937 -0
- vllm/model_executor/models/hyperclovax_vision.py +1206 -0
- vllm/model_executor/models/idefics2_vision_model.py +416 -0
- vllm/model_executor/models/idefics3.py +758 -0
- vllm/model_executor/models/interfaces.py +854 -0
- vllm/model_executor/models/interfaces_base.py +195 -0
- vllm/model_executor/models/intern_vit.py +481 -0
- vllm/model_executor/models/internlm2.py +453 -0
- vllm/model_executor/models/internlm2_ve.py +148 -0
- vllm/model_executor/models/interns1.py +832 -0
- vllm/model_executor/models/interns1_vit.py +418 -0
- vllm/model_executor/models/internvl.py +1423 -0
- vllm/model_executor/models/jais.py +374 -0
- vllm/model_executor/models/jamba.py +630 -0
- vllm/model_executor/models/jina_vl.py +144 -0
- vllm/model_executor/models/keye.py +1684 -0
- vllm/model_executor/models/keye_vl1_5.py +601 -0
- vllm/model_executor/models/kimi_vl.py +620 -0
- vllm/model_executor/models/lfm2.py +558 -0
- vllm/model_executor/models/llama.py +671 -0
- vllm/model_executor/models/llama4.py +732 -0
- vllm/model_executor/models/llama4_eagle.py +241 -0
- vllm/model_executor/models/llama_eagle.py +171 -0
- vllm/model_executor/models/llama_eagle3.py +292 -0
- vllm/model_executor/models/llava.py +872 -0
- vllm/model_executor/models/llava_next.py +572 -0
- vllm/model_executor/models/llava_next_video.py +479 -0
- vllm/model_executor/models/llava_onevision.py +945 -0
- vllm/model_executor/models/mamba.py +310 -0
- vllm/model_executor/models/mamba2.py +346 -0
- vllm/model_executor/models/mamba_cache.py +83 -0
- vllm/model_executor/models/medusa.py +219 -0
- vllm/model_executor/models/midashenglm.py +788 -0
- vllm/model_executor/models/mimo.py +191 -0
- vllm/model_executor/models/mimo_mtp.py +273 -0
- vllm/model_executor/models/minicpm.py +593 -0
- vllm/model_executor/models/minicpm3.py +230 -0
- vllm/model_executor/models/minicpm_eagle.py +391 -0
- vllm/model_executor/models/minicpmo.py +804 -0
- vllm/model_executor/models/minicpmv.py +1786 -0
- vllm/model_executor/models/minimax_cache.py +36 -0
- vllm/model_executor/models/minimax_text_01.py +1027 -0
- vllm/model_executor/models/minimax_vl_01.py +431 -0
- vllm/model_executor/models/mistral3.py +628 -0
- vllm/model_executor/models/mixtral.py +494 -0
- vllm/model_executor/models/mllama.py +1697 -0
- vllm/model_executor/models/mllama4.py +1079 -0
- vllm/model_executor/models/mlp_speculator.py +206 -0
- vllm/model_executor/models/modernbert.py +374 -0
- vllm/model_executor/models/module_mapping.py +72 -0
- vllm/model_executor/models/molmo.py +1569 -0
- vllm/model_executor/models/moonvit.py +663 -0
- vllm/model_executor/models/motif.py +345 -0
- vllm/model_executor/models/mpt.py +332 -0
- vllm/model_executor/models/nano_nemotron_vl.py +1395 -0
- vllm/model_executor/models/nemotron.py +509 -0
- vllm/model_executor/models/nemotron_h.py +633 -0
- vllm/model_executor/models/nemotron_nas.py +484 -0
- vllm/model_executor/models/nemotron_vl.py +655 -0
- vllm/model_executor/models/nvlm_d.py +203 -0
- vllm/model_executor/models/olmo.py +406 -0
- vllm/model_executor/models/olmo2.py +428 -0
- vllm/model_executor/models/olmoe.py +485 -0
- vllm/model_executor/models/opt.py +413 -0
- vllm/model_executor/models/orion.py +350 -0
- vllm/model_executor/models/ovis.py +572 -0
- vllm/model_executor/models/ovis2_5.py +644 -0
- vllm/model_executor/models/paligemma.py +414 -0
- vllm/model_executor/models/persimmon.py +345 -0
- vllm/model_executor/models/phi.py +357 -0
- vllm/model_executor/models/phi3.py +19 -0
- vllm/model_executor/models/phi3v.py +701 -0
- vllm/model_executor/models/phi4_multimodal.py +1478 -0
- vllm/model_executor/models/phi4flash.py +737 -0
- vllm/model_executor/models/phi4mm.py +1281 -0
- vllm/model_executor/models/phi4mm_audio.py +1254 -0
- vllm/model_executor/models/phi4mm_utils.py +1875 -0
- vllm/model_executor/models/phimoe.py +681 -0
- vllm/model_executor/models/pixtral.py +1348 -0
- vllm/model_executor/models/plamo2.py +1126 -0
- vllm/model_executor/models/qwen.py +363 -0
- vllm/model_executor/models/qwen2.py +526 -0
- vllm/model_executor/models/qwen2_5_omni_thinker.py +985 -0
- vllm/model_executor/models/qwen2_5_vl.py +1256 -0
- vllm/model_executor/models/qwen2_audio.py +492 -0
- vllm/model_executor/models/qwen2_moe.py +558 -0
- vllm/model_executor/models/qwen2_rm.py +122 -0
- vllm/model_executor/models/qwen2_vl.py +1512 -0
- vllm/model_executor/models/qwen3.py +344 -0
- vllm/model_executor/models/qwen3_moe.py +704 -0
- vllm/model_executor/models/qwen3_next.py +1298 -0
- vllm/model_executor/models/qwen3_next_mtp.py +285 -0
- vllm/model_executor/models/qwen_vl.py +795 -0
- vllm/model_executor/models/registry.py +891 -0
- vllm/model_executor/models/roberta.py +252 -0
- vllm/model_executor/models/rvl.py +103 -0
- vllm/model_executor/models/seed_oss.py +488 -0
- vllm/model_executor/models/siglip.py +524 -0
- vllm/model_executor/models/siglip2navit.py +688 -0
- vllm/model_executor/models/skyworkr1v.py +914 -0
- vllm/model_executor/models/smolvlm.py +44 -0
- vllm/model_executor/models/solar.py +506 -0
- vllm/model_executor/models/stablelm.py +344 -0
- vllm/model_executor/models/starcoder2.py +357 -0
- vllm/model_executor/models/step3_text.py +521 -0
- vllm/model_executor/models/step3_vl.py +1091 -0
- vllm/model_executor/models/swin.py +475 -0
- vllm/model_executor/models/tarsier.py +649 -0
- vllm/model_executor/models/telechat2.py +151 -0
- vllm/model_executor/models/teleflm.py +79 -0
- vllm/model_executor/models/terratorch.py +294 -0
- vllm/model_executor/models/transformers.py +883 -0
- vllm/model_executor/models/ultravox.py +667 -0
- vllm/model_executor/models/utils.py +770 -0
- vllm/model_executor/models/vision.py +125 -0
- vllm/model_executor/models/voxtral.py +789 -0
- vllm/model_executor/models/whisper.py +966 -0
- vllm/model_executor/models/zamba2.py +1056 -0
- vllm/model_executor/parameter.py +599 -0
- vllm/model_executor/sampling_metadata.py +597 -0
- vllm/model_executor/utils.py +97 -0
- vllm/model_executor/warmup/__init__.py +0 -0
- vllm/model_executor/warmup/deep_gemm_warmup.py +223 -0
- vllm/model_executor/warmup/kernel_warmup.py +83 -0
- vllm/multimodal/__init__.py +35 -0
- vllm/multimodal/audio.py +116 -0
- vllm/multimodal/base.py +219 -0
- vllm/multimodal/cache.py +507 -0
- vllm/multimodal/hasher.py +110 -0
- vllm/multimodal/image.py +130 -0
- vllm/multimodal/inputs.py +979 -0
- vllm/multimodal/parse.py +496 -0
- vllm/multimodal/processing.py +1921 -0
- vllm/multimodal/profiling.py +313 -0
- vllm/multimodal/registry.py +375 -0
- vllm/multimodal/utils.py +754 -0
- vllm/multimodal/video.py +312 -0
- vllm/outputs.py +517 -0
- vllm/platforms/__init__.py +263 -0
- vllm/platforms/cpu.py +353 -0
- vllm/platforms/cuda.py +731 -0
- vllm/platforms/interface.py +599 -0
- vllm/platforms/rocm.py +504 -0
- vllm/platforms/tpu.py +236 -0
- vllm/platforms/xpu.py +243 -0
- vllm/plugins/__init__.py +72 -0
- vllm/plugins/io_processors/__init__.py +68 -0
- vllm/plugins/io_processors/interface.py +67 -0
- vllm/plugins/lora_resolvers/README.md +16 -0
- vllm/plugins/lora_resolvers/__init__.py +0 -0
- vllm/plugins/lora_resolvers/filesystem_resolver.py +50 -0
- vllm/pooling_params.py +183 -0
- vllm/profiler/__init__.py +0 -0
- vllm/profiler/layerwise_profile.py +375 -0
- vllm/profiler/utils.py +148 -0
- vllm/py.typed +2 -0
- vllm/ray/__init__.py +0 -0
- vllm/ray/lazy_utils.py +22 -0
- vllm/ray/ray_env.py +72 -0
- vllm/reasoning/__init__.py +25 -0
- vllm/reasoning/abs_reasoning_parsers.py +202 -0
- vllm/reasoning/deepseek_r1_reasoning_parser.py +173 -0
- vllm/reasoning/glm4_moe_reasoning_parser.py +151 -0
- vllm/reasoning/gptoss_reasoning_parser.py +87 -0
- vllm/reasoning/granite_reasoning_parser.py +363 -0
- vllm/reasoning/hunyuan_a13b_reasoning_parser.py +245 -0
- vllm/reasoning/mistral_reasoning_parser.py +47 -0
- vllm/reasoning/qwen3_reasoning_parser.py +151 -0
- vllm/reasoning/step3_reasoning_parser.py +109 -0
- vllm/sampling_params.py +577 -0
- vllm/scalar_type.py +349 -0
- vllm/scripts.py +15 -0
- vllm/sequence.py +1465 -0
- vllm/tasks.py +11 -0
- vllm/test_utils.py +130 -0
- vllm/third_party/__init__.py +0 -0
- vllm/third_party/pynvml.py +6140 -0
- vllm/tracing.py +136 -0
- vllm/transformers_utils/__init__.py +24 -0
- vllm/transformers_utils/chat_templates/__init__.py +5 -0
- vllm/transformers_utils/chat_templates/registry.py +71 -0
- vllm/transformers_utils/chat_templates/template_basic.jinja +3 -0
- vllm/transformers_utils/chat_templates/template_blip2.jinja +11 -0
- vllm/transformers_utils/chat_templates/template_chatml.jinja +10 -0
- vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja +23 -0
- vllm/transformers_utils/chat_templates/template_fuyu.jinja +3 -0
- vllm/transformers_utils/chat_templates/template_minicpmv45.jinja +93 -0
- vllm/transformers_utils/config.py +1043 -0
- vllm/transformers_utils/config_parser_base.py +20 -0
- vllm/transformers_utils/configs/__init__.py +55 -0
- vllm/transformers_utils/configs/arctic.py +207 -0
- vllm/transformers_utils/configs/chatglm.py +72 -0
- vllm/transformers_utils/configs/deepseek_vl2.py +216 -0
- vllm/transformers_utils/configs/eagle.py +84 -0
- vllm/transformers_utils/configs/falcon.py +90 -0
- vllm/transformers_utils/configs/jais.py +238 -0
- vllm/transformers_utils/configs/kimi_vl.py +37 -0
- vllm/transformers_utils/configs/medusa.py +63 -0
- vllm/transformers_utils/configs/midashenglm.py +101 -0
- vllm/transformers_utils/configs/mistral.py +165 -0
- vllm/transformers_utils/configs/mlp_speculator.py +68 -0
- vllm/transformers_utils/configs/moonvit.py +33 -0
- vllm/transformers_utils/configs/nemotron.py +205 -0
- vllm/transformers_utils/configs/nemotron_h.py +259 -0
- vllm/transformers_utils/configs/nemotron_vl.py +56 -0
- vllm/transformers_utils/configs/ovis.py +176 -0
- vllm/transformers_utils/configs/qwen3_next.py +275 -0
- vllm/transformers_utils/configs/speculators/__init__.py +2 -0
- vllm/transformers_utils/configs/speculators/algos.py +32 -0
- vllm/transformers_utils/configs/speculators/base.py +91 -0
- vllm/transformers_utils/configs/step3_vl.py +123 -0
- vllm/transformers_utils/configs/ultravox.py +120 -0
- vllm/transformers_utils/detokenizer.py +169 -0
- vllm/transformers_utils/detokenizer_utils.py +199 -0
- vllm/transformers_utils/dynamic_module.py +60 -0
- vllm/transformers_utils/processor.py +245 -0
- vllm/transformers_utils/processors/__init__.py +16 -0
- vllm/transformers_utils/processors/deepseek_vl2.py +363 -0
- vllm/transformers_utils/processors/ovis.py +420 -0
- vllm/transformers_utils/processors/ovis2_5.py +458 -0
- vllm/transformers_utils/runai_utils.py +99 -0
- vllm/transformers_utils/s3_utils.py +90 -0
- vllm/transformers_utils/tokenizer.py +293 -0
- vllm/transformers_utils/tokenizer_base.py +149 -0
- vllm/transformers_utils/tokenizer_group.py +132 -0
- vllm/transformers_utils/tokenizers/__init__.py +10 -0
- vllm/transformers_utils/tokenizers/mistral.py +520 -0
- vllm/transformers_utils/utils.py +99 -0
- vllm/triton_utils/__init__.py +16 -0
- vllm/triton_utils/importing.py +95 -0
- vllm/usage/__init__.py +0 -0
- vllm/usage/usage_lib.py +259 -0
- vllm/utils/__init__.py +3438 -0
- vllm/utils/deep_gemm.py +212 -0
- vllm/utils/flashinfer.py +372 -0
- vllm/utils/jsontree.py +90 -0
- vllm/utils/tensor_schema.py +236 -0
- vllm/v1/__init__.py +0 -0
- vllm/v1/attention/__init__.py +0 -0
- vllm/v1/attention/backends/__init__.py +0 -0
- vllm/v1/attention/backends/cpu_attn.py +922 -0
- vllm/v1/attention/backends/flash_attn.py +800 -0
- vllm/v1/attention/backends/flashinfer.py +1128 -0
- vllm/v1/attention/backends/flex_attention.py +796 -0
- vllm/v1/attention/backends/gdn_attn.py +320 -0
- vllm/v1/attention/backends/linear_attn.py +68 -0
- vllm/v1/attention/backends/mamba1_attn.py +81 -0
- vllm/v1/attention/backends/mamba2_attn.py +224 -0
- vllm/v1/attention/backends/mamba_attn.py +52 -0
- vllm/v1/attention/backends/mla/__init__.py +0 -0
- vllm/v1/attention/backends/mla/common.py +1608 -0
- vllm/v1/attention/backends/mla/cutlass_mla.py +301 -0
- vllm/v1/attention/backends/mla/flashattn_mla.py +273 -0
- vllm/v1/attention/backends/mla/flashinfer_mla.py +110 -0
- vllm/v1/attention/backends/mla/flashmla.py +213 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py +255 -0
- vllm/v1/attention/backends/mla/triton_mla.py +175 -0
- vllm/v1/attention/backends/pallas.py +413 -0
- vllm/v1/attention/backends/rocm_aiter_fa.py +548 -0
- vllm/v1/attention/backends/short_conv_attn.py +82 -0
- vllm/v1/attention/backends/tree_attn.py +450 -0
- vllm/v1/attention/backends/triton_attn.py +430 -0
- vllm/v1/attention/backends/utils.py +834 -0
- vllm/v1/attention/backends/xformers.py +437 -0
- vllm/v1/core/__init__.py +0 -0
- vllm/v1/core/block_pool.py +330 -0
- vllm/v1/core/encoder_cache_manager.py +333 -0
- vllm/v1/core/kv_cache_coordinator.py +440 -0
- vllm/v1/core/kv_cache_manager.py +398 -0
- vllm/v1/core/kv_cache_utils.py +1169 -0
- vllm/v1/core/sched/__init__.py +0 -0
- vllm/v1/core/sched/async_scheduler.py +47 -0
- vllm/v1/core/sched/interface.py +158 -0
- vllm/v1/core/sched/output.py +162 -0
- vllm/v1/core/sched/request_queue.py +224 -0
- vllm/v1/core/sched/scheduler.py +1287 -0
- vllm/v1/core/sched/utils.py +69 -0
- vllm/v1/core/single_type_kv_cache_manager.py +670 -0
- vllm/v1/cudagraph_dispatcher.py +121 -0
- vllm/v1/engine/__init__.py +202 -0
- vllm/v1/engine/async_llm.py +757 -0
- vllm/v1/engine/coordinator.py +357 -0
- vllm/v1/engine/core.py +1245 -0
- vllm/v1/engine/core_client.py +1333 -0
- vllm/v1/engine/detokenizer.py +300 -0
- vllm/v1/engine/exceptions.py +17 -0
- vllm/v1/engine/llm_engine.py +332 -0
- vllm/v1/engine/logprobs.py +201 -0
- vllm/v1/engine/output_processor.py +558 -0
- vllm/v1/engine/parallel_sampling.py +133 -0
- vllm/v1/engine/processor.py +524 -0
- vllm/v1/engine/utils.py +857 -0
- vllm/v1/executor/__init__.py +0 -0
- vllm/v1/executor/abstract.py +126 -0
- vllm/v1/executor/multiproc_executor.py +683 -0
- vllm/v1/executor/ray_distributed_executor.py +109 -0
- vllm/v1/kv_cache_interface.py +275 -0
- vllm/v1/metrics/__init__.py +0 -0
- vllm/v1/metrics/loggers.py +717 -0
- vllm/v1/metrics/prometheus.py +82 -0
- vllm/v1/metrics/ray_wrappers.py +133 -0
- vllm/v1/metrics/reader.py +246 -0
- vllm/v1/metrics/stats.py +248 -0
- vllm/v1/outputs.py +147 -0
- vllm/v1/pool/__init__.py +0 -0
- vllm/v1/pool/metadata.py +77 -0
- vllm/v1/request.py +237 -0
- vllm/v1/sample/__init__.py +0 -0
- vllm/v1/sample/logits_processor/__init__.py +294 -0
- vllm/v1/sample/logits_processor/builtin.py +273 -0
- vllm/v1/sample/logits_processor/interface.py +97 -0
- vllm/v1/sample/logits_processor/state.py +161 -0
- vllm/v1/sample/metadata.py +43 -0
- vllm/v1/sample/ops/__init__.py +0 -0
- vllm/v1/sample/ops/bad_words.py +39 -0
- vllm/v1/sample/ops/logprobs.py +26 -0
- vllm/v1/sample/ops/penalties.py +43 -0
- vllm/v1/sample/ops/topk_topp_sampler.py +254 -0
- vllm/v1/sample/rejection_sampler.py +623 -0
- vllm/v1/sample/sampler.py +281 -0
- vllm/v1/sample/tpu/__init__.py +0 -0
- vllm/v1/sample/tpu/metadata.py +124 -0
- vllm/v1/sample/tpu/sampler.py +213 -0
- vllm/v1/serial_utils.py +395 -0
- vllm/v1/spec_decode/__init__.py +0 -0
- vllm/v1/spec_decode/eagle.py +740 -0
- vllm/v1/spec_decode/medusa.py +66 -0
- vllm/v1/spec_decode/metadata.py +62 -0
- vllm/v1/spec_decode/metrics.py +191 -0
- vllm/v1/spec_decode/ngram_proposer.py +157 -0
- vllm/v1/spec_decode/utils.py +14 -0
- vllm/v1/structured_output/__init__.py +297 -0
- vllm/v1/structured_output/backend_guidance.py +245 -0
- vllm/v1/structured_output/backend_lm_format_enforcer.py +167 -0
- vllm/v1/structured_output/backend_outlines.py +320 -0
- vllm/v1/structured_output/backend_types.py +134 -0
- vllm/v1/structured_output/backend_xgrammar.py +323 -0
- vllm/v1/structured_output/request.py +86 -0
- vllm/v1/structured_output/utils.py +373 -0
- vllm/v1/utils.py +382 -0
- vllm/v1/worker/__init__.py +0 -0
- vllm/v1/worker/block_table.py +221 -0
- vllm/v1/worker/cpu_model_runner.py +163 -0
- vllm/v1/worker/cpu_worker.py +183 -0
- vllm/v1/worker/gpu_input_batch.py +821 -0
- vllm/v1/worker/gpu_model_runner.py +3743 -0
- vllm/v1/worker/gpu_worker.py +697 -0
- vllm/v1/worker/kv_connector_model_runner_mixin.py +122 -0
- vllm/v1/worker/lora_model_runner_mixin.py +192 -0
- vllm/v1/worker/tpu_input_batch.py +585 -0
- vllm/v1/worker/tpu_model_runner.py +1947 -0
- vllm/v1/worker/tpu_worker.py +340 -0
- vllm/v1/worker/utils.py +290 -0
- vllm/v1/worker/worker_base.py +65 -0
- vllm/v1/worker/xpu_model_runner.py +53 -0
- vllm/v1/worker/xpu_worker.py +179 -0
- vllm/version.py +41 -0
- vllm/vllm_flash_attn/.gitkeep +0 -0
- vllm/worker/__init__.py +0 -0
- vllm/worker/cache_engine.py +145 -0
- vllm/worker/enc_dec_model_runner.py +553 -0
- vllm/worker/model_runner.py +2016 -0
- vllm/worker/model_runner_base.py +307 -0
- vllm/worker/utils.py +49 -0
- vllm/worker/worker.py +670 -0
- vllm/worker/worker_base.py +651 -0
- vllm_cpu_avx512vnni-0.10.2.post2.dist-info/METADATA +326 -0
- vllm_cpu_avx512vnni-0.10.2.post2.dist-info/RECORD +1395 -0
- vllm_cpu_avx512vnni-0.10.2.post2.dist-info/WHEEL +5 -0
- vllm_cpu_avx512vnni-0.10.2.post2.dist-info/entry_points.txt +5 -0
- vllm_cpu_avx512vnni-0.10.2.post2.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1395 @@
|
|
|
1
|
+
vllm/_C.abi3.so,sha256=TK7qTSfSQ8w0GSThyHV0N93BhRQZr6ODTSfSIVVfPUY,19355256
|
|
2
|
+
vllm/__init__.py,sha256=MQoYb7rYoeo-kX8Fp20iKGfIoOqnTXz5WOaWoRDbncU,8622
|
|
3
|
+
vllm/_bc_linter.py,sha256=RTr7MzNcfVt1cExZAjCU0_XddMsYLaVofVJ4rZbPpZg,1130
|
|
4
|
+
vllm/_custom_ops.py,sha256=pgWrK0Zm0J-1BFmD3v-neAPws_QvEc74ZsLEe18828Q,82195
|
|
5
|
+
vllm/_ipex_ops.py,sha256=4a8nH_qncMVIDKyH9O2Hk4L0nbtV-tcMOH_O0vkYNPw,14902
|
|
6
|
+
vllm/_version.py,sha256=_eXHsY0Q-5oZFWaL1G9JWwegcM02Lm1Tp6G5-cJzBwg,721
|
|
7
|
+
vllm/beam_search.py,sha256=SlhWsmeczGcDv_q8ahGzsuH-2UPSn5YJWLp4JudUuyw,2638
|
|
8
|
+
vllm/collect_env.py,sha256=Wp1V9YqqxKIRAk14w4OXuxeXPctrlK1Plnd9VvQDQsQ,28332
|
|
9
|
+
vllm/connections.py,sha256=YL5sQpi0vg05ZwNhpnn-7h9oCGjQeKWjTRYPCB_pKGQ,5088
|
|
10
|
+
vllm/env_override.py,sha256=8AjyisA4M-B6jf7_Fy3Jg2uEw3_YC1BCz4YfZwV8W5g,798
|
|
11
|
+
vllm/envs.py,sha256=5x6xZ_6-67Hgj2abKBnXh4O6mQPW5TBV1bTBXA7V8j4,56895
|
|
12
|
+
vllm/forward_context.py,sha256=tKxY4uVPReYWV0mG_NNnKeO5QVY8tJS5xLVlsOcKqEk,11062
|
|
13
|
+
vllm/logger.py,sha256=tvf9zwIBZ3h_rHiT73Ki3tR9xR2YF8UxCPxrCf0qPGw,8163
|
|
14
|
+
vllm/logits_process.py,sha256=l7EmiG8n4-zYS1ZHr3jnCJDHSvWUfXdfaIx7y6yYzXw,4440
|
|
15
|
+
vllm/logprobs.py,sha256=fINdiEWKd-jHejnSCCJdgjlJ_OntlmxBP1_5wa7S27k,932
|
|
16
|
+
vllm/outputs.py,sha256=TyjGeb9jENR-EMgf8P1rQa-j97vh9dR1ULSuGBdIfHw,20247
|
|
17
|
+
vllm/pooling_params.py,sha256=ZuZmWOe1qhV8cC3Zp-kew7oub_UE8O0zBHXdytVq1M4,6616
|
|
18
|
+
vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
|
|
19
|
+
vllm/sampling_params.py,sha256=hMOvJrGUsYUl4kfnSTQbkdC_rUmmwQn388mziHf9Bc4,25449
|
|
20
|
+
vllm/scalar_type.py,sha256=WJBNCrw9FJN1X4v8XthULwPl9Z06D3E0Lp6e9QyhVpw,12486
|
|
21
|
+
vllm/scripts.py,sha256=GBLs96wGlHWNj7WDtb-kuwHCR7HCdQIJN-vDoPh2Ud8,501
|
|
22
|
+
vllm/sequence.py,sha256=y_jiR6YydgDmlOpZFKpdmYB7VKr3Mmebd9tIwonikk0,57678
|
|
23
|
+
vllm/tasks.py,sha256=VT3C8VC8S7yL8fxhxjjXGPZWOhsYmiuGjUJTSeqSscQ,398
|
|
24
|
+
vllm/test_utils.py,sha256=7JwK7zXL7i_ucUeSEjpdlBNuWgccueXrqrowwd7g7j4,6063
|
|
25
|
+
vllm/tracing.py,sha256=xSfM1V5r4pQ7UJ5ZINIPx35C6D26xLt3PlskVpfLioQ,5113
|
|
26
|
+
vllm/version.py,sha256=j5_jpV6lcpUIkq56JF2uxJS02TJjG_7nGrzjvf7ptDI,1375
|
|
27
|
+
vllm/adapter_commons/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
28
|
+
vllm/adapter_commons/layers.py,sha256=ahfExqPZiZfRoi8gmzp31Hj3MKGvcalVGGR6w9lhdNA,450
|
|
29
|
+
vllm/adapter_commons/models.py,sha256=5XvXSRMnC8TufQZwf7O01SH83chilebej3Y4LnQKrhU,2870
|
|
30
|
+
vllm/adapter_commons/request.py,sha256=PGKCbvlRywX4PTQgT9hPBGYwkc9scpiic-Hi3K6Uokg,686
|
|
31
|
+
vllm/adapter_commons/utils.py,sha256=eAbRtVVso5fvSLp28k9VjArFUjrbl8BT0NkJPmJIgF4,3329
|
|
32
|
+
vllm/adapter_commons/worker_manager.py,sha256=PKuagBEoFxWzPz9AbUogHGaNJst7mWlAOarcZkUBa7I,992
|
|
33
|
+
vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
34
|
+
vllm/assets/audio.py,sha256=03OUK2QRgJDgEucc2HDl3vdrwgiRAuBxzckas015Ces,1254
|
|
35
|
+
vllm/assets/base.py,sha256=Yv1bK5DmfZbWr_1Uqhb-mawh5M6yC1tlFT6gRkHtcgs,1265
|
|
36
|
+
vllm/assets/image.py,sha256=X9uLm_fdT8IPGHvyFoBh1yTjmy1bWfFuYlkP1C75KdY,1570
|
|
37
|
+
vllm/assets/video.py,sha256=8COC_9jHMLbGGGz9mKcrP8DGs7peQagQG5JvhiPZfA4,4155
|
|
38
|
+
vllm/attention/__init__.py,sha256=kYUvfkDN8O2FIlSpXs-YYgCDa7wkyjEQbopsFebcO18,662
|
|
39
|
+
vllm/attention/layer.py,sha256=1UCHpUbptvPSPMd54U6qBIAnBk1NIPFpRGVjyC6uHgs,22774
|
|
40
|
+
vllm/attention/selector.py,sha256=plVEcTzgHZmUpBWA4keZEXOPMUij4NRO80rqIEFHIck,7828
|
|
41
|
+
vllm/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
42
|
+
vllm/attention/backends/abstract.py,sha256=yy4Q8rrM7TE185EIQULLPIyf9HfXOTGCSn74QHsOVLU,11094
|
|
43
|
+
vllm/attention/backends/differential_flash_attn.py,sha256=4Fnea1d-U0kpwA7VpD386MNQV2U0rngc1V99iryLjmo,42221
|
|
44
|
+
vllm/attention/backends/dual_chunk_flash_attn.py,sha256=M2Fs8DGzxqDd_md-HzMlCWY38nCVGpWnSJ_T-n_z48U,66267
|
|
45
|
+
vllm/attention/backends/flash_attn.py,sha256=guNOot9Dj308MIlMsSbkN1eQi2GifvuKKWe1URiErEM,41543
|
|
46
|
+
vllm/attention/backends/flashmla.py,sha256=XI80Cke7Www52KyOBK-WX9p2Pc-yoU4s-1sEGcS-ZKA,9008
|
|
47
|
+
vllm/attention/backends/placeholder_attn.py,sha256=CxsoIFE2tfuMUdQPiUMKMUCTqLxll1V5vrbRSSAPcnM,13478
|
|
48
|
+
vllm/attention/backends/rocm_aiter_mla.py,sha256=Fy_RcJJEPXwZfudzdgdx72p15mDGJaqabxElw1fahSE,16943
|
|
49
|
+
vllm/attention/backends/rocm_flash_attn.py,sha256=WJt0TKdUOcBVTkKwTygvz-Cx_5VeoK2V7IoqBB6jtIE,41609
|
|
50
|
+
vllm/attention/backends/triton_mla.py,sha256=ZSw3Ftc_9i_b7ZzL2Gv-ei2bDNgqjeL9dm27rKDBBHw,3929
|
|
51
|
+
vllm/attention/backends/utils.py,sha256=0m3r2qyrQNhfbHVJOqggeEDD7U_Dz2RJXohq8SAq0uE,26001
|
|
52
|
+
vllm/attention/backends/xformers.py,sha256=-eZcG59i97rZGsKUyx_oa7tZUUicWYhjRKD2gL9v9TA,33922
|
|
53
|
+
vllm/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
54
|
+
vllm/attention/backends/mla/common.py,sha256=6hp411XTFIsZ2o7qEzhy8gm2Fdo7Ab5u8qVGsf3azAY,54305
|
|
55
|
+
vllm/attention/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
56
|
+
vllm/attention/layers/chunked_local_attention.py,sha256=97g1ljvV8wNXc3Et95-TSLTmQxjE7Ft6eX88H8qSbWE,3420
|
|
57
|
+
vllm/attention/layers/cross_attention.py,sha256=QdVvjgbQsii_dNjuHiE3aCSgzr0Lp-5R8namT8LIjUk,5938
|
|
58
|
+
vllm/attention/layers/encoder_only_attention.py,sha256=F31atlHXMQm2HAReWZ5K_XkDnZhZgc6Sr2o9QuHs6I0,3225
|
|
59
|
+
vllm/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
60
|
+
vllm/attention/ops/chunked_prefill_paged_decode.py,sha256=a4Hyg_vF_3QvbuYxgVIhkOCZu60ndEFiCfB0TtH5zak,13610
|
|
61
|
+
vllm/attention/ops/common.py,sha256=dqO3X8rpHulPAZUSnA5ugzVM_azKI0RkMbqppzgZvWs,4515
|
|
62
|
+
vllm/attention/ops/flashmla.py,sha256=iprdol7K1hKHu-wcVmAzuReJrEJ1o7fsAVkIqsH6Qr0,4315
|
|
63
|
+
vllm/attention/ops/merge_attn_states.py,sha256=1ed_lE3BuH_ahf1PW4d0I6izUasZuKbQdKSeVLu6ESw,1706
|
|
64
|
+
vllm/attention/ops/paged_attn.py,sha256=ub6HAIi7OaezmLV7wlIhhHIhR-qR6ffYBghGqfTtdy0,8553
|
|
65
|
+
vllm/attention/ops/pallas_kv_cache_update.py,sha256=aHiYya1JXNCULxzQRS0qP1JHCfsW_kXVKf8w7cQwFNw,4232
|
|
66
|
+
vllm/attention/ops/prefix_prefill.py,sha256=gFX53IC-FyesklWsii5WXvCONXIyXgtp4XCyJJtLeJo,32191
|
|
67
|
+
vllm/attention/ops/rocm_aiter_mla.py,sha256=xfSzRsAYlysmHNIszg_df1JMsV-zURso0PLwwGABo94,3697
|
|
68
|
+
vllm/attention/ops/rocm_aiter_paged_attn.py,sha256=NofcR9IMgoqBVT-iyHNNFmJCmq6pv41deXucZcF-WPg,3954
|
|
69
|
+
vllm/attention/ops/triton_decode_attention.py,sha256=4SJu0yifb9S7nV48V7qA4xxSx7HvTTHOKaPQI1Nrg2w,19251
|
|
70
|
+
vllm/attention/ops/triton_flash_attention.py,sha256=qt0ss9DjryWVXSdAIdxoDK-KiqKso3yd_CzSnhHT5aY,32379
|
|
71
|
+
vllm/attention/ops/triton_merge_attn_states.py,sha256=gKRLVpClXSa4wBO3HkFk4OBKtUPaNOUq7oJkKHQ5X0o,3563
|
|
72
|
+
vllm/attention/ops/triton_unified_attention.py,sha256=wuEvVTJ8TLARvHa5Gp5OdZTIp-IZraH4tDQp-P-Kddc,30680
|
|
73
|
+
vllm/attention/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
74
|
+
vllm/attention/utils/fa_utils.py,sha256=mUY49jb7iOVtOZGtZV0mZ0-eZMVq0PdM-j_EfcSqwVA,3192
|
|
75
|
+
vllm/attention/utils/kv_sharing_utils.py,sha256=UsGA1xmBsfJlCrPwFA-28bydHX2f895hTPWzIQ44x3g,1701
|
|
76
|
+
vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
77
|
+
vllm/benchmarks/datasets.py,sha256=oz3ej_GhsM6UAky_mJymi0LPbzBtH8l55QMrHYIRfE4,101578
|
|
78
|
+
vllm/benchmarks/latency.py,sha256=OwiM2sNAdWK9NFWoq8kKR5EqbTnPjBeN2rov6jAWJVI,6141
|
|
79
|
+
vllm/benchmarks/serve.py,sha256=ZFA5PIpJ41K-sVmVtLV9du_MkW9QoiD8QLTZ4J3wDlM,48676
|
|
80
|
+
vllm/benchmarks/throughput.py,sha256=7eHkhlYV5jRMPipalQNLqh5w1L063Vw8B6hnWi6xOPc,28109
|
|
81
|
+
vllm/benchmarks/lib/__init__.py,sha256=BlbNrv7ga0LXYeHLKKiey2woiGh5MkW36g7QG6L6BN0,142
|
|
82
|
+
vllm/benchmarks/lib/endpoint_request_func.py,sha256=lARvj6BcP5g3G_F3hHXbjaBVzKmoW7asYFvjgQsGEws,18301
|
|
83
|
+
vllm/benchmarks/lib/ready_checker.py,sha256=Xr7gMBu67J2KeTeaLCe7TK2iIiYjEf6a0mldRE9Sum4,2357
|
|
84
|
+
vllm/benchmarks/lib/utils.py,sha256=sNpbrvBcediO7xu5nU-WqPdmzDf9KW0QsaERbtDtFX8,2522
|
|
85
|
+
vllm/compilation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
86
|
+
vllm/compilation/activation_quant_fusion.py,sha256=RAtMRhOSJo8fKC3bnt-69IsSmBSBH4e52i_w9cMdZOc,7101
|
|
87
|
+
vllm/compilation/backends.py,sha256=Jf5X99WTZGRRiZJfNH9hH2ZRPsvn8wF0zY5wkiwSv6g,25824
|
|
88
|
+
vllm/compilation/base_static_graph.py,sha256=QDsEcNw-rjLB74h8QCue6e8Z8wpFso20LzMyvPZLM7Y,1917
|
|
89
|
+
vllm/compilation/collective_fusion.py,sha256=4Vhc7JSXTowleyK4MmyjOHMuEssBV4kkAI1NV5D17bM,46503
|
|
90
|
+
vllm/compilation/compiler_interface.py,sha256=hciT_2g9Wv62OKYRfxrobsxluo9MSW8qMRCgQIuy7ls,23557
|
|
91
|
+
vllm/compilation/counter.py,sha256=vBHbjJRU8z2Us8uUL6n4jxNesQLuRQrASkCdn1Kxydo,1612
|
|
92
|
+
vllm/compilation/cuda_graph.py,sha256=YWVPrRkWb4aX1Pgk67g6rx7iL9JSFUuXNlXeZOdhdt8,8785
|
|
93
|
+
vllm/compilation/cuda_piecewise_backend.py,sha256=oCBTmpLy6LArUrrrAE3UB0qkE3JyX4pwQ2_NU7Vav6E,4422
|
|
94
|
+
vllm/compilation/decorators.py,sha256=vpkPOX79nLzzuMaJdknFSmYKJwbKT__72LQ8J0o6VgY,12861
|
|
95
|
+
vllm/compilation/fix_functionalization.py,sha256=5Hr86yvJL0FIfaKN4lT8wTv3B76j6lfpZJzH4kLI5b0,9329
|
|
96
|
+
vllm/compilation/fusion.py,sha256=SIVqfYkrMoQ4RyS2EDBh25uCSFiUieAwLIv5wGzjPmo,23968
|
|
97
|
+
vllm/compilation/fusion_attn.py,sha256=AMCykYaMcvLM5Tl8PLc99Q0V2JFBHOJFw_ZUU_xs6PU,12435
|
|
98
|
+
vllm/compilation/fx_utils.py,sha256=NTw_6bSgwkGsBuCyWfNU-KC8kzd2BOueEQNpD_s69bI,2931
|
|
99
|
+
vllm/compilation/inductor_pass.py,sha256=-eJV4R2z15_NFDT8jwN6SCO93BQCoNoK9Yq-UQVgxWI,4094
|
|
100
|
+
vllm/compilation/monitor.py,sha256=npXL2K-tPC01q0WrUbqqr3mme4HWrk7upPTc_2RzYqk,2065
|
|
101
|
+
vllm/compilation/multi_output_match.py,sha256=uuVLvzaBuEZjOLbrfQVH9tZvaBD2GdNwbidSNaWv9dY,3904
|
|
102
|
+
vllm/compilation/noop_elimination.py,sha256=vwhCcnl4LKwBAg70Au9gA24I__tA5EiGGpa18C6JVMw,6579
|
|
103
|
+
vllm/compilation/pass_manager.py,sha256=W5n4irerCq4ajfqaL56eNE7g-0Pgct9bGNPk4lm1c5w,3375
|
|
104
|
+
vllm/compilation/sequence_parallelism.py,sha256=dfi9Wo1KahtEN76bmRNd4-jZdDg6moAH3sSTxXaMznk,18845
|
|
105
|
+
vllm/compilation/torch25_custom_graph_pass.py,sha256=OTZc1hc3eLlS8LhG4MvHwpglY5_1E_voPW7ShGS5HJs,1430
|
|
106
|
+
vllm/compilation/vllm_inductor_pass.py,sha256=1HwtrkTskhTcvpINykO_862o8mQWan93ones_qEtjEw,1524
|
|
107
|
+
vllm/compilation/wrapper.py,sha256=xXw0qP1RjXpxayHUNrNaN-t-VUgt_lNPvbugrl7ALho,6094
|
|
108
|
+
vllm/config/__init__.py,sha256=Jhc3wC3Chy9rqRuXH_TXt8Q3eVVJWEoWRx7bQKKZbZo,170318
|
|
109
|
+
vllm/config/cache.py,sha256=xciX6XrU5A0fT-jkgaASTOFVS00CxguKtoxA_sagBAA,9989
|
|
110
|
+
vllm/config/compilation.py,sha256=6drA8IzwFrNrYen4c9Aj48mmUNeUEysVHoDRynqT9_0,25784
|
|
111
|
+
vllm/config/kv_events.py,sha256=r5T4niCkwkJISARBzhANMwctJeM-k8EkWHE2ZFrSvkM,1446
|
|
112
|
+
vllm/config/kv_transfer.py,sha256=3lsnU3h8_LhafFR1NvsVRXWLeoyfH86yhFPt0OxKlCw,3989
|
|
113
|
+
vllm/config/load.py,sha256=MilccTna8lHdLiqRsNCFOV2mDSRQY1buTyVK03BPyCs,5213
|
|
114
|
+
vllm/config/lora.py,sha256=Lak9ay1x3lNNUtk-IgDN-pNoDND8xrY8cA0EuU5idPs,5596
|
|
115
|
+
vllm/config/parallel.py,sha256=qYvF99ZPx2yzYWfIzSEU4j356J_Eqo-SyC0YK_uZ2Vs,20596
|
|
116
|
+
vllm/config/scheduler.py,sha256=q8g08KwUeBvnCnzJHjiwxEPIqldlFb1HdwJZNOkhazM,13420
|
|
117
|
+
vllm/config/utils.py,sha256=rdZC5HFsXJc4wf0N9dPkXAUCO7U1eOZerqVQSL7ooeM,906
|
|
118
|
+
vllm/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
119
|
+
vllm/core/block_manager.py,sha256=A_kQ6M1NqgujTzxYIVv8aX-dMtRggL-bctJR8m1cWfg,22296
|
|
120
|
+
vllm/core/evictor.py,sha256=PpSG_eUcFqtVjRPcEh9AUCOtAFQSB0eHfOidUlKfU-M,5516
|
|
121
|
+
vllm/core/interfaces.py,sha256=ONM6fWByKR3Kbl37MIfZLYxQA5RHbnOt8BomFeDIs0M,3770
|
|
122
|
+
vllm/core/placeholder_block_space_manager.py,sha256=ORG0voTO36PriADYHn08Tvl24USqY4tOEp3mQ-SD4Ac,3134
|
|
123
|
+
vllm/core/scheduler.py,sha256=YYRygUc77gvHRPLkQA6_vgAidhWT92At4wB7Pg3E3Nw,88654
|
|
124
|
+
vllm/core/block/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
125
|
+
vllm/core/block/block_table.py,sha256=Yokf5KU-onU1gp7dlqfWa0mQlCbtx9vNceGcg1dFDDg,16091
|
|
126
|
+
vllm/core/block/common.py,sha256=nTf2wtA0nWtbGoh5qsN8XmwIP8r9xlP8ry1lInaZTRY,13269
|
|
127
|
+
vllm/core/block/cpu_gpu_block_allocator.py,sha256=mcW0zUL82k3ffiHw5uKempc64z8RRQOSTW1-uuMhRTE,16881
|
|
128
|
+
vllm/core/block/interfaces.py,sha256=BLv8rVkTVINbae_-Y5MLKUuZK-9Tix5qxlMRcb1jMRY,8213
|
|
129
|
+
vllm/core/block/naive_block.py,sha256=wdIFPx3QLMW-oDicQGzlQEbGQ0WhfPG9-tqWapQ8SaE,16428
|
|
130
|
+
vllm/core/block/prefix_caching_block.py,sha256=iggQyho_9aReD900xvGDyRAjrBfDnAAkZgSqlk2SEmY,44252
|
|
131
|
+
vllm/core/block/utils.py,sha256=ecLOYLGeBIeqMCpbUNBoW6hJIHlG5EINgsf2Or1BHyk,997
|
|
132
|
+
vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
133
|
+
vllm/device_allocator/cumem.py,sha256=_IAlRPernOmR4PDcGxhUT3g85blMmb8_xSVGJzaudqQ,11364
|
|
134
|
+
vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
|
|
135
|
+
vllm/distributed/communication_op.py,sha256=igCBXNoAhJ8eZooR79KhpzgYlVP1TUgnPF5C7BSpSJE,1562
|
|
136
|
+
vllm/distributed/kv_events.py,sha256=IyzLUC18jtO25Vt9wN1tgrTGuqhjfhCGK3HSYNyPBPI,12540
|
|
137
|
+
vllm/distributed/parallel_state.py,sha256=boSsuf0hF6EP2tH3QzwE-LVDRxDck227qCUGcx1TJAs,57843
|
|
138
|
+
vllm/distributed/tpu_distributed_utils.py,sha256=OOCkNrzouRGPCot0UMVeQPKSbBhXZnNaaRz1c6VKimE,7827
|
|
139
|
+
vllm/distributed/utils.py,sha256=K2CNfdyDZChfy6QWoMx-n6pDzbG8X4SBmdutEnhPNqQ,21012
|
|
140
|
+
vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
141
|
+
vllm/distributed/device_communicators/all2all.py,sha256=2_QnBmK0xWzi8ygdhwmjVYG_HNvf7i6hPwKkyptG6q8,9596
|
|
142
|
+
vllm/distributed/device_communicators/all_reduce_utils.py,sha256=obR-KUiMvP2wduqdaljapLdlNm-6ivS4C016TmLenDE,11306
|
|
143
|
+
vllm/distributed/device_communicators/base_device_communicator.py,sha256=u3dCh84hf9YhThP40ROFCDlCR-xSKguPm1fmt2Cqt6Q,10968
|
|
144
|
+
vllm/distributed/device_communicators/cpu_communicator.py,sha256=WsVwXfEcvKUnr1mdXIVMWicUDjT0mOywRc7VqvLK7kw,7526
|
|
145
|
+
vllm/distributed/device_communicators/cuda_communicator.py,sha256=vzPLNsM4-K__wa5Mo3BUW4Grq3U_JH3mr84hF-E__NE,12279
|
|
146
|
+
vllm/distributed/device_communicators/cuda_wrapper.py,sha256=1I1OZOc9-St5Zlr4gUmoDm7HxdS-T9ZE1ixOJGJK55s,7185
|
|
147
|
+
vllm/distributed/device_communicators/custom_all_reduce.py,sha256=oGX3FYfd7sUWbe63Ho-hTDybnX2pWHT4LIwIlON-s60,13095
|
|
148
|
+
vllm/distributed/device_communicators/pynccl.py,sha256=Q6YpOystctZakkv2uoKQKt1UIn6WAldX74mmDKkrO7w,11910
|
|
149
|
+
vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=mse8xJPxEqJG7Wf29j_mFC4y4IcORRYXDlIp9bAKlJ8,15657
|
|
150
|
+
vllm/distributed/device_communicators/quick_all_reduce.py,sha256=-TnB_helsIyosJoUMdIg7bfJKe6AbKXQPBjxirHMLtQ,10886
|
|
151
|
+
vllm/distributed/device_communicators/ray_communicator.py,sha256=Uf3R1QuZnyvBIRekkJwKnol_biT1gpFTIMPLlH000IE,9167
|
|
152
|
+
vllm/distributed/device_communicators/shm_broadcast.py,sha256=x4C6QKStqUotHdkmI5OjcqWR24gA3U07v8V3t8EmC6Q,24959
|
|
153
|
+
vllm/distributed/device_communicators/symm_mem.py,sha256=WbkQyerbeoOba7XMMulf4AxdvIguYD0SBVE0K1PmUKE,4878
|
|
154
|
+
vllm/distributed/device_communicators/tpu_communicator.py,sha256=dIWViwqW3r-7C76aYzkFV6VquFv1dtBGiwDpuMtAVrE,4251
|
|
155
|
+
vllm/distributed/device_communicators/xpu_communicator.py,sha256=dne6oe74zS-29LgBobQfyXtgDG_nQy9eWvm3RQCNsbs,2725
|
|
156
|
+
vllm/distributed/eplb/__init__.py,sha256=iDRi-3lUn2DaLMC9aCQ1xdvvLrRNpT1YFieBjVnYKr8,213
|
|
157
|
+
vllm/distributed/eplb/eplb_state.py,sha256=2-rru9IZqzFpjnkotc9MyWBO4xr3No25BvFcT78yVEE,23225
|
|
158
|
+
vllm/distributed/eplb/rebalance_algo.py,sha256=eqMleLcYqoXWL_WZDqAVhWU3tO-1NPVwicu45wwDpRQ,8952
|
|
159
|
+
vllm/distributed/eplb/rebalance_execute.py,sha256=xpM7VBgya6q9kJuMDEv1YNc1E2KvTgPYQlE-2VatrvU,14997
|
|
160
|
+
vllm/distributed/kv_transfer/README.md,sha256=cKIw6vXYSxBlf0wWwO7haP82CX2oB2QzW0-RxZE5mT4,2007
|
|
161
|
+
vllm/distributed/kv_transfer/__init__.py,sha256=Ahm9bFQ6fpDLzOzgx2pQq90i4o5OUu25_hYKE4-PHwA,525
|
|
162
|
+
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
|
|
163
|
+
vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=UHvTyR3qsB6qEuR8zJ5lO7nF31RYGPhjIfCoKRRb3WA,2294
|
|
164
|
+
vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
165
|
+
vllm/distributed/kv_transfer/kv_connector/base.py,sha256=KuKixI9XMfNTMWanVED-kedkMyMFtdcT34QO26lweJ0,370
|
|
166
|
+
vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=mTT48FrdTvasEjBXK8cTjniU3AJAFvRZ0jFh_HeI6sU,3986
|
|
167
|
+
vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=sh_ESqf_TlRE68GGdnYhX99vp-UTwVqfiIVgnQkTaro,9814
|
|
168
|
+
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=Vgcn88rEfiLwJ3-YkZKWsvMurr-vsV4_47b9_Mv-vlo,265
|
|
169
|
+
vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=xffSvnOYq6uMbC2Z2TbvJGVUw7bV3hUu8GXvvSqjJy0,12783
|
|
170
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=rNyNeaBmdNANrY1Q87NuDYd6zKGF0Yc2eJysQKOLxm4,6514
|
|
171
|
+
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=aiLRixTSIWhIRpd7UEgEpevtC4ivRiJ1eqA1QJqJnzA,10926
|
|
172
|
+
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=wCXyAbFALpoqK3ZQwTlylgm5ubyKW8ctUDeo5wCOaeY,59169
|
|
173
|
+
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py,sha256=yUWUyovumlB7eMwm7TfzqrJkP0H4afYLVbNPpQW-Dq0,17132
|
|
174
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
175
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py,sha256=le7kvhrjAiuwkdXrsff3_EG-r_xnZr3S8yDaPX34eZc,18598
|
|
176
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py,sha256=C3RSZaBOHP01tscrTTKCmVMrmSTLeQ5Wi-6CJs2CMXc,21788
|
|
177
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py,sha256=r5qfxwK0bQkypRujF1NIgCF8j1T--99qzveGc-Io-6s,9367
|
|
178
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
179
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/base.py,sha256=ZZYJZBDDny_StDcmXUFwOtDslRrTCL9iSUcr8XWe08g,6280
|
|
180
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py,sha256=atXfrR3n4MZAB88TtNmVAC5Gn9FhyVFcVRO1VjjL4uA,5679
|
|
181
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py,sha256=m8XNP5UiFwq2g33f3fiJeLMu87OhKwSvjWcI2jppztk,9156
|
|
182
|
+
vllm/distributed/kv_transfer/kv_pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
183
|
+
vllm/distributed/kv_transfer/kv_pipe/base.py,sha256=FHfg3C53oZjBBZjEWHmxMOPKTvJitfBOXXFzh8j70cU,2156
|
|
184
|
+
vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py,sha256=_yti48_vO7pZ9VxyLNr9AuzQRJi16-SBebDdlWotkAM,12402
|
|
185
|
+
vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py,sha256=ZSRrodfeNUaHKRbPiHMpfOBM5Ms06vQnF9HcP3MASzU,9732
|
|
186
|
+
vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
187
|
+
vllm/engine/arg_utils.py,sha256=ovtuS-_uc8LpIljPoyWmizakccf4bSmoJfNfSQRRI60,86260
|
|
188
|
+
vllm/engine/async_llm_engine.py,sha256=uD40885N3WJnjgcdD-jKRjarYc1AqVPLY_hQRv8SgKo,42236
|
|
189
|
+
vllm/engine/async_timeout.py,sha256=uxUlhUevs6Ae1VvJ0GTkj23bAkg_w_CWteeXTCAFYvM,6594
|
|
190
|
+
vllm/engine/llm_engine.py,sha256=jhboJCfAX-EGd4c8pQhYBj43MUEQe_2VH_swPD8K-Jw,79551
|
|
191
|
+
vllm/engine/metrics.py,sha256=byNIc20pfiWhoYOrXpAcDQ2RwEnPK4jsjYQ2f3UXbdE,24293
|
|
192
|
+
vllm/engine/metrics_types.py,sha256=MKvHu_x4U0ZVvDv5KTmIRTfMuHhCqkPNPqGX6ISEgrQ,2737
|
|
193
|
+
vllm/engine/protocol.py,sha256=dCClKykvLl7pCjulB-rpK39fZu3ipmDMInsI9oytQGc,12444
|
|
194
|
+
vllm/engine/multiprocessing/__init__.py,sha256=0ER1-OLg21FcZ6koLkfaccB5ZmlWTBjuTO5IkE8OMZk,3510
|
|
195
|
+
vllm/engine/multiprocessing/client.py,sha256=9tgctkmncBXZhI8GNg0b5do6C3xP88rcfJOjgNVmvOk,26092
|
|
196
|
+
vllm/engine/multiprocessing/engine.py,sha256=CAW5qzG_9cqxf9ljWKTNUqqWlN1aTXy8m809vb6qtBA,18791
|
|
197
|
+
vllm/engine/output_processor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
198
|
+
vllm/engine/output_processor/interfaces.py,sha256=dbWAaMazkJTagXU005QLlf9RF-NgeEGzKKP6a8AQHP8,2495
|
|
199
|
+
vllm/engine/output_processor/single_step.py,sha256=W11dmtv_-7wwuDafhgUdLR_Hf6GHrg56pmQI6LHITj4,6422
|
|
200
|
+
vllm/engine/output_processor/stop_checker.py,sha256=wPsxTqC2x2HkggUrTtnme3DL37gdwVZ37SDspMsdWTo,5137
|
|
201
|
+
vllm/engine/output_processor/util.py,sha256=358XXxAOG9vNO6uRTfINK0B-oCzqbidVpXfV5nrNs2k,1125
|
|
202
|
+
vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
203
|
+
vllm/entrypoints/api_server.py,sha256=F1c5uZ-WFzmNtrpSH158bOzv6p623tmY7gimPZiwMGY,5818
|
|
204
|
+
vllm/entrypoints/chat_utils.py,sha256=BaZPqGruzXXzuk3VaH8LdRlSQ3eIoteJxpkqmJVs4dc,51603
|
|
205
|
+
vllm/entrypoints/constants.py,sha256=ZX2zFNKkQjQM46StHeaSFaQIJEToSYcyJ7EBr98ZpWs,335
|
|
206
|
+
vllm/entrypoints/context.py,sha256=HSL1Brt3aisw4uruFXjH3KZ5LSJGgY_6oMXDMae84Go,17754
|
|
207
|
+
vllm/entrypoints/harmony_utils.py,sha256=KwcOEoI57zAsJGS8QXJJSL40B3_ODWMDCbGZa01aVQk,17097
|
|
208
|
+
vllm/entrypoints/launcher.py,sha256=WMBw5HKaKihs_mvCBiq8Ps-m7Zk1qo6wE4wNSio9UDU,6272
|
|
209
|
+
vllm/entrypoints/llm.py,sha256=7wBFHdMpEjFIG6Uw5NA0J4FuAVtx6xlzQ16SP7BVOuU,70862
|
|
210
|
+
vllm/entrypoints/logger.py,sha256=-2pe5uquycCb6BR9gsCI1MBfuGmVSZ_nhfFj8huMoxo,2527
|
|
211
|
+
vllm/entrypoints/renderer.py,sha256=cVPZN2_L0jNW-NCML3SSRFeaFhnBJU7wCeiNnewbYL0,15253
|
|
212
|
+
vllm/entrypoints/score_utils.py,sha256=xAIWZww6Ual6cOeqaWhskza2MVvuJn2r35s5QZ8t5D0,8009
|
|
213
|
+
vllm/entrypoints/ssl.py,sha256=2InxP04Dt_I84ORXewngn5cUdXvRkrK_zZB6o8Ng60k,2805
|
|
214
|
+
vllm/entrypoints/tool.py,sha256=twgXy0yY2t1Cvx9YlUmvVJu0phNxEPLqYda987RA7So,4552
|
|
215
|
+
vllm/entrypoints/tool_server.py,sha256=G9TaulKUSUGQ4Eee5FrOMV9Ug5zkCh3OMD080aiLIto,6859
|
|
216
|
+
vllm/entrypoints/utils.py,sha256=b0P_gDn5Hl_CL9Zr51aUunZKe_vtnAY2D7F10xVR8q8,13571
|
|
217
|
+
vllm/entrypoints/cli/__init__.py,sha256=GRsSDBSSOHMLZfY8jjf-h5gFMOaOaicDAgcIGCVZdI8,482
|
|
218
|
+
vllm/entrypoints/cli/collect_env.py,sha256=GebDsiNF6qvxWrzz8RaQdOnHZtFeoDnNGCMrSvq5krA,1069
|
|
219
|
+
vllm/entrypoints/cli/main.py,sha256=UlcbgyfvJx6h0f3aM5MLlMD4cbnjDqPBE4sZ1NfN2no,1761
|
|
220
|
+
vllm/entrypoints/cli/openai.py,sha256=eTNWi8X0vqpJg0xNoc19VitcFu5xAKpEN7ZTQUIZPEs,7189
|
|
221
|
+
vllm/entrypoints/cli/run_batch.py,sha256=mMDDXRcW7PAxX06bNL908Mi2LwFH8Lv6q0DEKd_8jLs,2403
|
|
222
|
+
vllm/entrypoints/cli/serve.py,sha256=TeVIpV_zsJQY7f185s1BHnT8e0DlNx1gv0XWQQH9onc,9046
|
|
223
|
+
vllm/entrypoints/cli/types.py,sha256=horNt6_2wEsuLNQ1-zoQ3BWsMkvMxJAxcTC-eQS4O1E,785
|
|
224
|
+
vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
225
|
+
vllm/entrypoints/cli/benchmark/base.py,sha256=r1QkRTjaUCcjO78Zw9zuDeRhMdaGw22N3hqO8kgrOsI,674
|
|
226
|
+
vllm/entrypoints/cli/benchmark/latency.py,sha256=MYxv7pF4kq6StJN5uZYxOm51lIHfNyvMIvXU--szia4,653
|
|
227
|
+
vllm/entrypoints/cli/benchmark/main.py,sha256=IWYHShB_3jDLgk8cFj64xaqpXhPSjSuiYHEw6C8TwNk,2036
|
|
228
|
+
vllm/entrypoints/cli/benchmark/serve.py,sha256=izuara3nwC64MtoealX_FzR9cB6u4YQv0fDikj-VdNI,635
|
|
229
|
+
vllm/entrypoints/cli/benchmark/throughput.py,sha256=YN5PAz4aDjxXkao1a_RjrR8hLGzzjYPecO_OIp1TVwQ,652
|
|
230
|
+
vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
231
|
+
vllm/entrypoints/openai/api_server.py,sha256=QLEkX8-loY8hWiMvwlyZKT8Ww32snEvwI41JoWFNdWM,77634
|
|
232
|
+
vllm/entrypoints/openai/cli_args.py,sha256=LPfLVuCNlpMAt-KtoOv9-4co4RzAmzxb0ZIxyPw4v-o,12682
|
|
233
|
+
vllm/entrypoints/openai/logits_processors.py,sha256=QAJn3DMAfFySExoA5aaSNVjXwtlOXGCv1DX6Fltj2ZY,3230
|
|
234
|
+
vllm/entrypoints/openai/protocol.py,sha256=Kut7D0itpvMLq8BWvcqv4ZDWPyIbbKKap9-SWryQzZc,95911
|
|
235
|
+
vllm/entrypoints/openai/run_batch.py,sha256=Oc5GgroFkBREC5_mn_Cuwcey8F7L-yhYI2RLAmoPajQ,18694
|
|
236
|
+
vllm/entrypoints/openai/serving_chat.py,sha256=r_laDF3_n92H2M1THIH0cd48QvNt3WO8ZaC30F_1O-s,75624
|
|
237
|
+
vllm/entrypoints/openai/serving_classification.py,sha256=GKZVbHwWb_13hIl9aeH5dkEyxg7l0jONc1HtbRcYDD0,5958
|
|
238
|
+
vllm/entrypoints/openai/serving_completion.py,sha256=KIi3MRnwTRvKGHWBq8G_cn5JJ2u_tmtgtf8rULeZhek,29632
|
|
239
|
+
vllm/entrypoints/openai/serving_embedding.py,sha256=FrHP8gNq2LqpphXlpQi-o2D1ufjUawPONtc7F4B-EQw,26223
|
|
240
|
+
vllm/entrypoints/openai/serving_engine.py,sha256=r-RCy9UUAGCgW3GUBOAu8WHq_zxWY70Bh3cdm9w3zw4,36858
|
|
241
|
+
vllm/entrypoints/openai/serving_models.py,sha256=s3pgymW5GFPRSloTErKzX0ed90_SElhYhclkh5nMLg4,11558
|
|
242
|
+
vllm/entrypoints/openai/serving_pooling.py,sha256=h3sY2OlY5xEESVdm3u3kSQ2c4ourYs_JjyvmRF7Gmjc,10847
|
|
243
|
+
vllm/entrypoints/openai/serving_responses.py,sha256=jyMH5ll_h8viQHrWWpWDe7_gBlZKW-gY_q6PPPpyMyQ,76432
|
|
244
|
+
vllm/entrypoints/openai/serving_score.py,sha256=dTh2LZaJaq5NF0YB5ZNNwOaGiXvyWSo2hJtq6CCQktY,17968
|
|
245
|
+
vllm/entrypoints/openai/serving_tokenization.py,sha256=SBa6g4A9is3F-UE_vDlUeNQsnoXJLSKZUlIUvUg_iTw,7642
|
|
246
|
+
vllm/entrypoints/openai/serving_transcription.py,sha256=gNGsdcznBTwf2Ij3jwxlKnPKfX0WSviMIUQJzKersGY,5600
|
|
247
|
+
vllm/entrypoints/openai/speech_to_text.py,sha256=avKA7WZPF5NuqVQikQ4P3D1V8KvTewElLcZLzBXRZdE,16436
|
|
248
|
+
vllm/entrypoints/openai/tool_parsers/__init__.py,sha256=iwZF_3D9qUuzt1oYCoJ2jN69jZ9EXgNV2l-DxJu5ZW8,1923
|
|
249
|
+
vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py,sha256=UyO8engPSTh8Ej8EuQay-mDz9YPzHAsmzJA43-4vmq8,6095
|
|
250
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py,sha256=deOUIIVsaEVAAf6CyBBeaTbEDc4LNnIMwh4rIOIXtlA,16522
|
|
251
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py,sha256=Tgr__jUTZFKNbX5JJ7GM_aI4yyOTtSsXdRy2g_It5mI,16688
|
|
252
|
+
vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py,sha256=dmRFoDMlYZ819f3Y0GGRq-oGlzZIjmi2Xh7Dy1REcHk,7881
|
|
253
|
+
vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py,sha256=JUDqbsw7CAMDSFqViqCio1fiAttQxf8VNmpZet_4WV0,11498
|
|
254
|
+
vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py,sha256=biTD8_t7Hg86-rksZb7qm7Yj3ovbYohUIOJzq6_9cF4,10719
|
|
255
|
+
vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py,sha256=DyJHDoYiP_0BNz4sJ3ELBiq8aDwROOLDTE7kanbXyOM,19237
|
|
256
|
+
vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py,sha256=PaIJ3YqCz5h-QSlCWiAMSDzrHV5GEQvSi7g0sTLVewo,16238
|
|
257
|
+
vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py,sha256=qELeSPWN0h7lSuUNMhcnaJSjBR16m9sXFIgIQHyxZ0k,9460
|
|
258
|
+
vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py,sha256=3B7JF2J6CQ-pW-QPusclBAXHjRYpXIkdK_6tG-9P5Go,13943
|
|
259
|
+
vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py,sha256=TIXaxhjXo6C-aF3oYG_p42-yLKeK6fISInZME4Om9sA,17076
|
|
260
|
+
vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py,sha256=BQ0YsnJ9-bLFmAvc-GCjNkXZsx8Euc7PMBVDh6maiZo,13257
|
|
261
|
+
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py,sha256=pJ63Xb6B4zitFeYPVXzjf4ZoGBOlog5EtJY3tn_nHcI,12505
|
|
262
|
+
vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py,sha256=ZKChv22q8JaS9bM4KuWhlpZIuuAwMBaBSLKuNHbHieU,29330
|
|
263
|
+
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py,sha256=hb63cYdfoWNUJ2Igyvi1h-d9peONMBmd7gaX-LKD7SA,16545
|
|
264
|
+
vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py,sha256=0zCdbN9s930BvEqXUNpOLrFG2WnF-rxungSIuCTr_EY,2662
|
|
265
|
+
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py,sha256=ul0h98fxIIgo8Ugj4NA5Vh5atgl40CvfIypVHL3IAmQ,4342
|
|
266
|
+
vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py,sha256=yXO5XGgV1j0QmyFoaYGLeUrD0R5XrvV9yLfmu_HYLLM,12635
|
|
267
|
+
vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py,sha256=XbuLexCQQbTITBnMB5phgSOKyRqs-FV-yDLZBD3u7W4,32119
|
|
268
|
+
vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py,sha256=XZOOXDXeXjgjBfrojFpIu1yEpS19SEYFE_7Skkv32_I,30531
|
|
269
|
+
vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py,sha256=fgfd05Xflm6fuxMiqF8xh5yAotXudTfAsEaGhbYi7nM,12512
|
|
270
|
+
vllm/entrypoints/openai/tool_parsers/utils.py,sha256=RrvMsSpaYYMPefvM1ktVKzo9Gs5KsHpi21QaP1h4EKU,3874
|
|
271
|
+
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py,sha256=zzp0l-1cIREuCHDy0Cn0aZIgfJN1JOTvoM03i5coUEQ,24599
|
|
272
|
+
vllm/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
273
|
+
vllm/executor/executor_base.py,sha256=eRTsJC7Zbsu7qK36zUbIkBfzHzcoU-1lOQ7URY-CYiM,14739
|
|
274
|
+
vllm/executor/mp_distributed_executor.py,sha256=3mXwyo56RLUEtNMu2eHI4jC04O6derFqlauxfVmaq_4,9924
|
|
275
|
+
vllm/executor/msgspec_utils.py,sha256=Mq3r85TXhqff3ljqOzlnGmIj3gmOaGNFQor6ugyzW_w,1209
|
|
276
|
+
vllm/executor/multiproc_worker_utils.py,sha256=-SrsMwbr__d-NY8zCJywMVqvUqKW8GoqDHIqNalEbdM,9720
|
|
277
|
+
vllm/executor/ray_distributed_executor.py,sha256=kZIp7XJvX4hhLb0i3Bksh5v2R2gAl6cwnF23d2RwWTE,31011
|
|
278
|
+
vllm/executor/ray_utils.py,sha256=je_lfNCYC5vfPqx2IHagjxF7OZA9QI1Og1jCSRBoByo,17475
|
|
279
|
+
vllm/executor/uniproc_executor.py,sha256=k2TWyEpK2boOxAD-tELiZ39pViFDSpx4o7RvXNgwz8E,6061
|
|
280
|
+
vllm/inputs/__init__.py,sha256=MBSr_DUD06q5O5Gtc9nRwWBqgm09ZOrj7cCx7iiIXLY,1412
|
|
281
|
+
vllm/inputs/data.py,sha256=0WTh3bBYcGA4qchOfVYCQb0_fln4zUIDIDnplFG4hDA,11724
|
|
282
|
+
vllm/inputs/parse.py,sha256=_Lbf4PQyczm3OPsLgvyPf3CiKGNP1Ctd4bW_AnuORpk,4499
|
|
283
|
+
vllm/inputs/preprocess.py,sha256=-FYjCGdPHyDHKDq15K4lfc7TXYcm8TOJoLBZPzao4UM,35925
|
|
284
|
+
vllm/inputs/registry.py,sha256=CGiOvFmHg26olQlBsMrVtQqHPnx7nY1BpOsqNNp2lNI,8140
|
|
285
|
+
vllm/logging_utils/__init__.py,sha256=lGnFUwOOIQYnuCu-Pf3LKtxPRmx6DgkxlxknU9fO3-Q,205
|
|
286
|
+
vllm/logging_utils/dump_input.py,sha256=g9nr91If5qsBTNXuKD9FeCOs8Z9N4zsj-kMpJISODKk,3071
|
|
287
|
+
vllm/logging_utils/formatter.py,sha256=Yi12ADzbS9tI3J_pFhTevzYb6zFVgs4JQZI6uIY64_M,2847
|
|
288
|
+
vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
289
|
+
vllm/lora/lora.py,sha256=AuAxQNXr-6RLCn7Kc28qqbgA715IDb7yfuReHchu10I,6294
|
|
290
|
+
vllm/lora/models.py,sha256=ti5AcPONvE6rIG-gaNWqigrHO7Vfrv1STyxLk63A6Yc,34604
|
|
291
|
+
vllm/lora/peft_helper.py,sha256=H9FY8VNaxEkKM-BjBsw_z1g8jDI2NSmFy6N4--LjDWo,4871
|
|
292
|
+
vllm/lora/request.py,sha256=spYbJvjKyPlu1a1otY3sxI4JBpAzUvLLjhyxFJP2Cg0,3178
|
|
293
|
+
vllm/lora/resolver.py,sha256=6iZpDMfxWGcy8MWlj3nCCcVmgr6nKs8EzzOhaN4TiCs,2881
|
|
294
|
+
vllm/lora/utils.py,sha256=VwuKftS-kwksgBYN-ACC40SuP-KHtO2a8RVqMSoWd_w,9413
|
|
295
|
+
vllm/lora/worker_manager.py,sha256=mK7hOz-g5szmjUwq2Uekt1Y0YWWHWrcDmMXrPn2HNdU,10972
|
|
296
|
+
vllm/lora/layers/__init__.py,sha256=tE8Jprt4oSDFBvhCL7ydkKZrszspefYPdxNqfgvHv2Y,1471
|
|
297
|
+
vllm/lora/layers/base.py,sha256=fN0rPYPWhz-Udi5dnRB_j6J9Uo9CIULm_JkYsUWK1Ic,1944
|
|
298
|
+
vllm/lora/layers/base_linear.py,sha256=whD9iKfDSCkasEj_yRT7FxxpbOQlRQDyIIfihVYrP9A,6999
|
|
299
|
+
vllm/lora/layers/column_parallel_linear.py,sha256=1VO7Pc50L0ncMdhKtftg-9akF3SBoITqAdc7SaKsgDA,23848
|
|
300
|
+
vllm/lora/layers/logits_processor.py,sha256=JvC7_aoxD3TmZL5b4d8xV4ey8g_z9GajYMSPVLfaTC4,8537
|
|
301
|
+
vllm/lora/layers/qkv_x_parallel_linear.py,sha256=inUvsOTycDKUXpbQiZ_i34PhW1qeYNCDjeh58c3boLk,233
|
|
302
|
+
vllm/lora/layers/replicated_linear.py,sha256=IaymTlelvZOMXMrsycZ1pVCdJIbETEOzdcmaPixqD8Q,1846
|
|
303
|
+
vllm/lora/layers/row_parallel_linear.py,sha256=51DBCeoDHTf1TiJ5NdpjXD_q1YeMcW9s7c-z1TWEOaI,7179
|
|
304
|
+
vllm/lora/layers/utils.py,sha256=AiMHZZJj-PgM5tiKeMuodB7yHzw6it6M9UXa4dg4SFk,1838
|
|
305
|
+
vllm/lora/layers/vocal_parallel_embedding.py,sha256=8oUQRccOCFsMDHx8MKlnHUDA-erob_ikMoXqro6lTJc,6434
|
|
306
|
+
vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
307
|
+
vllm/lora/ops/ipex_ops/__init__.py,sha256=BGJ5bmli1rUC-Bc-vKw7zC4GHWeJu_vFetmC-sUo1_8,306
|
|
308
|
+
vllm/lora/ops/ipex_ops/lora_ops.py,sha256=MRGhU-LHiQhWXXRW1ZB9jklfkYV6WY4OGnAVANZYat0,1593
|
|
309
|
+
vllm/lora/ops/torch_ops/__init__.py,sha256=ywu1d5miStgp7A9BRAo6kUvuE3AcgOAOJHxYHD4cKvQ,535
|
|
310
|
+
vllm/lora/ops/torch_ops/lora_ops.py,sha256=LOSdfKpQM365cIWVkyElcLpfgn8cF44IVw-KUN2NMKs,4517
|
|
311
|
+
vllm/lora/ops/triton_ops/__init__.py,sha256=arDrNt_kvrDaC4mN3RNbu6-0YACXQRp9Md2cJxXI1ao,384
|
|
312
|
+
vllm/lora/ops/triton_ops/kernel_utils.py,sha256=3P-CWMjNQR2vp3QUNynjXAIaWQy06mEFDTRLRQljDME,8509
|
|
313
|
+
vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=UlZGGZGVxH8lC6wYqVsEmIqrczlTGvUNLHjOPwXMWSo,9059
|
|
314
|
+
vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=YgL-K9fVeFZebx68DJNvrqsfZI5o0thpa---d4NYlnA,5967
|
|
315
|
+
vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=u2ZJ0gsXE2YFy6N3jLkr8Z4fS3_4zDKisTVl-LZ11S8,8090
|
|
316
|
+
vllm/lora/ops/triton_ops/utils.py,sha256=Ljg-GwRcsGZruXe3fsdqu8RE2rZDOTd4duH4a2nPW4c,5216
|
|
317
|
+
vllm/lora/ops/xla_ops/__init__.py,sha256=2Yh5hqiUt7hGz9SwznSZlj-_G7-SknTauNyHGDcUjBY,304
|
|
318
|
+
vllm/lora/ops/xla_ops/lora_ops.py,sha256=hLERTyHuXcH5J5ePn_3cak2Mi5S8_i0BcXiJmNZHBEk,4400
|
|
319
|
+
vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
|
|
320
|
+
vllm/lora/punica_wrapper/punica_base.py,sha256=buFvKbdfl3bJcyJKiIIpnpE5mTunBfsMIMnCLjbU0Xo,17298
|
|
321
|
+
vllm/lora/punica_wrapper/punica_cpu.py,sha256=sFBBu_qBEL8LGALamK7hE1ympyipYNT4qpav-V1nllU,12527
|
|
322
|
+
vllm/lora/punica_wrapper/punica_gpu.py,sha256=F0VIK01RS5HGUIu-cGpgw5fN7pgGWnCjFf6njYBQ-_c,10603
|
|
323
|
+
vllm/lora/punica_wrapper/punica_selector.py,sha256=Of6p5uYMMLnA6g46VK7M3xJT8Xq4q1VFoeOpTIsPf3s,799
|
|
324
|
+
vllm/lora/punica_wrapper/punica_tpu.py,sha256=HI_4c7mpNH9ZmPwlVOHqQuUk2aXw8vTI5CnkO_O0CWs,15580
|
|
325
|
+
vllm/lora/punica_wrapper/punica_xpu.py,sha256=abBmR7Dnr7tGYBN_ZJ7TYnyV5GjYHn962UsJAUB_aS8,10427
|
|
326
|
+
vllm/lora/punica_wrapper/utils.py,sha256=bBA7sN1SI2lw48b8TJLt82gwmgS69NSNDxdb2vzRRsY,5568
|
|
327
|
+
vllm/model_executor/__init__.py,sha256=vE7mcT8ZyKWc-wlc4pq2-ofRwEDVYT67HSgD-hLut0Y,574
|
|
328
|
+
vllm/model_executor/custom_op.py,sha256=Wmk_LAbhh0T4XUuZFfvoiqctSdUd6bkdVik7X7MdYFQ,7532
|
|
329
|
+
vllm/model_executor/parameter.py,sha256=gi-oWvdZjMnUFK_xm9kBoYWWfTzQNnqmzFTEA7_LWa8,22622
|
|
330
|
+
vllm/model_executor/sampling_metadata.py,sha256=WWqsW4AwPWcmN4tP0P_HKf1QdD8etKmrzmJtzA_IUFQ,23014
|
|
331
|
+
vllm/model_executor/utils.py,sha256=Ncn3v_38TrS3v-kdU6ElFSz-VHqiHhoRzsG4f69HLdg,3563
|
|
332
|
+
vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
333
|
+
vllm/model_executor/layers/activation.py,sha256=WlFMeC4fXe3DJmqJKlAAPRAsSrXkqjanab784sBy7mg,20611
|
|
334
|
+
vllm/model_executor/layers/attention_layer_base.py,sha256=bDN8w5Suq8j2C7xOG-xc9dS3XMfpqOphWPMKazGxEVo,715
|
|
335
|
+
vllm/model_executor/layers/layernorm.py,sha256=mLrlbC6L4CpDn2Yi3eJvxaw7OaA6G4DZAHuXHCQz1l0,12217
|
|
336
|
+
vllm/model_executor/layers/lightning_attn.py,sha256=PLUhvCJT2-ujjnSPfZ6AXK33V66Z3Eruuy3FeJZHYCY,21156
|
|
337
|
+
vllm/model_executor/layers/linear.py,sha256=x5djKPUpNVwuWD8sYma_pvi8Ji36IUj_CJ4I-E343tU,67658
|
|
338
|
+
vllm/model_executor/layers/logits_processor.py,sha256=JYmpMSZwP-j_yT8e_R2VZNLAgxOrE1d6pm7xfmoq-Gs,7958
|
|
339
|
+
vllm/model_executor/layers/mla.py,sha256=E5ZQArnUJ-fK8tY14d6U-b5vBnoX911UafZ0VS-EgSY,5871
|
|
340
|
+
vllm/model_executor/layers/pooler.py,sha256=vVxuDq7OTUKml2s8KnI5YJONC9dlF4mbYvqe62ux10U,24277
|
|
341
|
+
vllm/model_executor/layers/resampler.py,sha256=jDG2clcusNHfxLptLZUbbwxmxC3f_I-KJ8tJIdjyuLM,10506
|
|
342
|
+
vllm/model_executor/layers/sampler.py,sha256=70ZwO6MN2LJTju8siaPcbXz9OI4O4yMThj7URQtnb-Q,49421
|
|
343
|
+
vllm/model_executor/layers/utils.py,sha256=vRPDtB1RCoczly3vc2Up1FiVUCyigxkjlafyrDP0eAg,7369
|
|
344
|
+
vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=0lY477KsIQAXIBPxkqntqzAnUDqPGASVnH7xGA9Nrnc,22790
|
|
345
|
+
vllm/model_executor/layers/fla/__init__.py,sha256=Xbv6P8KG7bLpcOF17zPO5PYYHImweE9aiYYgGyMS9U4,391
|
|
346
|
+
vllm/model_executor/layers/fla/ops/__init__.py,sha256=Tx9ajmbsCCptuJofX-QpCC_Ut2SwZBTT56SUjGXGNs0,642
|
|
347
|
+
vllm/model_executor/layers/fla/ops/chunk.py,sha256=F9ZSa0TANKOLmICyibK2dak49zNkIO6PZrQBEnVbbWE,9482
|
|
348
|
+
vllm/model_executor/layers/fla/ops/chunk_delta_h.py,sha256=z5DwEoIzTsdB15uVlKuuu_qp2UeMaICWKu8JXrWIJIU,11155
|
|
349
|
+
vllm/model_executor/layers/fla/ops/chunk_o.py,sha256=S656q3AJeqpM2-bN4LTQMrj3LfjO8gOp4HIYtitnFhw,5239
|
|
350
|
+
vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py,sha256=2it3RIhRTd7Rt6RuzdzfHZVFIyv6jqIq6mFnCh5IUoM,4555
|
|
351
|
+
vllm/model_executor/layers/fla/ops/cumsum.py,sha256=86UJl0V-dxqJ8fiAhAjMLnh38JsFivYAMNpcWjbWKhE,8869
|
|
352
|
+
vllm/model_executor/layers/fla/ops/fused_recurrent.py,sha256=5xnE2M4itCJRujccwai93KmLDJXN9lyCrHEahxkFHEs,12700
|
|
353
|
+
vllm/model_executor/layers/fla/ops/index.py,sha256=Lgr5AFHESHhsvgCwQwcAluSBoW2fXte2XjyExBikRas,1266
|
|
354
|
+
vllm/model_executor/layers/fla/ops/l2norm.py,sha256=FR8gjI7Rc3Ahzbxpjc7cUj6of5dyzEqF2aDqsK0ZDEk,4024
|
|
355
|
+
vllm/model_executor/layers/fla/ops/layernorm_guard.py,sha256=pqhp1evGXs0VlEE3-MHaf3ghyyhhmUT41VCp6x-nQx0,11537
|
|
356
|
+
vllm/model_executor/layers/fla/ops/op.py,sha256=7l3ZIAw4i4f6VsmMR8QcbDRD2G-9BCbkdQFj9vv_wT0,1074
|
|
357
|
+
vllm/model_executor/layers/fla/ops/solve_tril.py,sha256=HBubDK4Rq1qK9KZjzqBnoMSYqnxV2ZGaPNA4x6CcAP0,15368
|
|
358
|
+
vllm/model_executor/layers/fla/ops/utils.py,sha256=_f_kk6e-KthBPPggp_-9hI2IV-V6n9PJ5PdgKyxttT4,5980
|
|
359
|
+
vllm/model_executor/layers/fla/ops/wy_fast.py,sha256=YfOPsfu7CPC6NcRd-nHR664d5NG-HDimD0IKZBiP9_k,4280
|
|
360
|
+
vllm/model_executor/layers/fused_moe/__init__.py,sha256=IyRctJ-x1jdf-7ioeTKGE-Du4cLYuwybnRtIJkS2h1Y,2637
|
|
361
|
+
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=_gx9APAHRtGFw_CUWJC2QkBV7zaf4t0LI6vyQ-P9HlI,10528
|
|
362
|
+
vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py,sha256=4f54J0blJtlMlSn0hQlSOmZ9_JnDTcrnJcZMl_smSCc,6737
|
|
363
|
+
vllm/model_executor/layers/fused_moe/config.py,sha256=NVnXNEugrk6vnPrA6JQ5cRdlka0FanyOxRQUan9ADTE,17360
|
|
364
|
+
vllm/model_executor/layers/fused_moe/cpu_fused_moe.py,sha256=-89Jc5mtsLNuultvYS8l1ww8lUHWKQHEyVO7gbbQnYo,10941
|
|
365
|
+
vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=tos-MbRwHQ3xZauPl7-vAPN8h_3kWb_BQhq7O7MojZo,36701
|
|
366
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=FCXExfkKG0HbtPvi1ISgP-08eENTxGJYXjP4KOmnLEM,13646
|
|
367
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_utils.py,sha256=i6wE2J38oTU5JiSqJvcjJGCZxjeYbuKkt3XAvP9U_zs,13936
|
|
368
|
+
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=SR3BFvLacbcDf8mHPR3MUCetqJ8VjHLoXSd7vcHCOKQ,10726
|
|
369
|
+
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=ODkRjU6DuWeSYu3tpqmvPH7Vlfexb-8Zbnc6aACA_x0,8648
|
|
370
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py,sha256=B3wGEVaWlyeC323Z5PUX4M_UvSvN1dq839e6vgjEXsE,8911
|
|
371
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py,sha256=zr0ALdbH80623Tkb_z4scSm0PnGfuIMqobg3FDloPKs,3438
|
|
372
|
+
vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=NQ1lX9Lh_XR84JqUJf7R-LhInhycQEN-ajVNCOfDqRw,34569
|
|
373
|
+
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=m0_S158YdD2cmqWrXCrMjhfgtsQ-wO0ONWRFz9UJiOs,9620
|
|
374
|
+
vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=CiqyHcIsU9lRCq7VPrHl2lcI470ygZSNZ_tvFo8218s,83522
|
|
375
|
+
vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py,sha256=v7iXsShJ2WRSOgfnbC4-uPkbfCuEqsHsrHcTglaxnOE,8333
|
|
376
|
+
vllm/model_executor/layers/fused_moe/layer.py,sha256=9qdBz4ACjxDCYczccqtUtTAfhlyzocxSCWVkWct5YZg,84089
|
|
377
|
+
vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=PRfkUmUjtIQXAsRrPDyDo8Ih1V35sMwCj49lop5DtUQ,34367
|
|
378
|
+
vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=rAvSB8cd6NtanQk8vNL7fLkpL3ul0sacX_BBIZk8aR8,3985
|
|
379
|
+
vllm/model_executor/layers/fused_moe/moe_pallas.py,sha256=-OiAA6igR4VE9FbrEHBtxc8Ugzt85uX9_7ubsmciatw,3163
|
|
380
|
+
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=XDZHXEkfWKAW1GFwOR3pzM0NzbwhKD--Iy335T6E4XI,8766
|
|
381
|
+
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=ZSvVVU8rUzENLnHycTypPg2UhO9eF_eu6wm1HEtpl-s,2156
|
|
382
|
+
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=8n7FF8zpepfNF-mqojXc8LxSrsXy5OV6TEF-A_Sr-XQ,11004
|
|
383
|
+
vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=mq61l6lsCj5kDhcXx4jwP4MiSj7eR2DY4Ibwr9bAyEw,2558
|
|
384
|
+
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=kEk3FQBVx9hVeCMhbWb3u4kkDRQLXxa_FlLmdRJWl_8,14958
|
|
385
|
+
vllm/model_executor/layers/fused_moe/routing_simulator.py,sha256=mccQRQsqTHTglvzrD8cUY8Z4q_CH9yWZf8itmbdJ0so,10487
|
|
386
|
+
vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py,sha256=-9BidYNhyAjc1ddZwRiQv4Cm1MIdEw28a_ifm9k8qXY,5750
|
|
387
|
+
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=IdWOyC-GSjNEw7XW3iA4pG51WcAO4dmHpTZ_hbMnr8o,6320
|
|
388
|
+
vllm/model_executor/layers/fused_moe/trtllm_moe.py,sha256=5vYMka4JkECoqmRBnD2cVM2-UY2Cft18FseuCl56klQ,6472
|
|
389
|
+
vllm/model_executor/layers/fused_moe/utils.py,sha256=Bnty0ZtfrpgrJYsxZSsA4lfgusUJ4QpWPgSYJCRdjXA,9116
|
|
390
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
|
391
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
|
|
392
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=qPumkNxaHMvVBnEjPe_Xiuz9ICb6Hqc-9I1DAR8s3gA,4130
|
|
393
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
|
|
394
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
|
|
395
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Np7yRX9Z7Y7Z5Nutbl02wpKdZRltbt4WqlPlleiYs2E,4146
|
|
396
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=XsNfNXY8v0eatazkLCDiDclI0FnTudUGLYO01e1_4aA,4149
|
|
397
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=H0K4_O1CMbNLi-srcycT3lSl4JaBl3EGF89GY5Rj9MU,4130
|
|
398
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
|
|
399
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=wjnQ4v-dflJMR3iFDHBuZI_1R0xXjsNoWc2kHu6C8JI,4135
|
|
400
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
|
|
401
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
402
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
|
|
403
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
|
|
404
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
|
405
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
|
|
406
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
|
407
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
|
408
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=LCN-mYQ8xqL_ewIGV95k6EC_dfJtcdfQZp8uZR9Air4,2721
|
|
409
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PvRpT_brUV3Y3zMfWEcsXMmdrYKjiq2qI9iHejPhhsU,3743
|
|
410
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MCTOhQ01id6YjPtWbG6Mw5dlU1xtilsiq3HAstGn36w,3258
|
|
411
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=3o_aYn580j2L0ZPdKSTLqrYnginfBOFNhCksS5qxeNA,3258
|
|
412
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qbqjisJ4oKmcYzumHPRk5UyOzsdi8J6xas82UWHMeAI,3263
|
|
413
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PflsK6VWRhwGaDKSIQ9vD7NMHcKLg3B4wENarR0aIq4,3252
|
|
414
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
|
|
415
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
|
416
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MlpzcrkZo78kFYr6cqmh4lBdpxKcEvlzqvRf0bmeduQ,3264
|
|
417
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
|
418
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
|
419
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
|
420
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ZrC8J_AmZWNx30UDrXG6sHWtFY6FNVPsNywLhEBQdi0,2530
|
|
421
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rN55MyeJ8U6VGNRg7lwC3aa8BgjxdzVg-CofcZ7LTyk,3743
|
|
422
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HqskM2MV6SPZ5LskeOY50lOjFP0DFdYrgRpZFmTpWTo,3256
|
|
423
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=L7y3Ev8CbIF-68FWhoMvK9HH72bj6r6-09__zxK-fvo,3257
|
|
424
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=IuvyC8TNhCVAmUZfLSoETsyCKsmejKXrs_0zuwFLPAU,3265
|
|
425
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Nd2qn9-7yjO6vAQSHAuetP4ytysnd6UxekL8UADiLKg,3254
|
|
426
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
|
427
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RFH5FcN2ZCPk6DsxviTti1Q8JU5jzBRFXvUQNgOvnmI,3265
|
|
428
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
|
429
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
|
430
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
|
|
431
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=Pux4G7sjfPL22uOJU6t35TXe-VU3OaoPA97TDj9_wZQ,3251
|
|
432
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json",sha256=he873aoOy7KfFg-uMoTFV4IP7Yk0Dk7mOTuLCTqwZZc,3250
|
|
433
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
|
|
434
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
|
435
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
|
436
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
|
437
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
|
|
438
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
|
|
439
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=h57svdmDlZC_D8w9XWjPRS8ciYVkJiPEYfhrD2NRVVY,4127
|
|
440
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
|
|
441
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
|
442
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
|
443
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=bWR6XBZ4nJ_ROg8rEgrQGc04I3BDbwILDHMZxATO-H4,2740
|
|
444
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Gu1wROuky-xS0dsFgbXS2QD_hOVV8yol9a5iqiYyq3s,2749
|
|
445
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
|
|
446
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=2ONiQSa9odzdPe1dIgBpP24l5z-5wB1eos06xOj0V_Q,2738
|
|
447
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
|
|
448
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=THQWP1o2bWhnJh0rq3ZIVvs_sagIJgoK4x3pJbiFbHk,2910
|
|
449
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=o1pR3rNpO1eW4BHOKpPIQLjviw4P2X5Fr4HQBcdHA-I,2747
|
|
450
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
|
|
451
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Uhq0SrWiCrldkWbb0ZZZhWaCZ0SsvpiNL4z30KZUN5g,2747
|
|
452
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ydsFUdXdVE_ZSScVhUxvxOFwKG-nkTraNeN69wqzxIM,2903
|
|
453
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
|
|
454
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json",sha256=u09XGUdUQqSDasrUgOQeu7ydp5ft5US1oSM0iT-BT3M,3235
|
|
455
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=JBO_l8hfxCbiQ_PvoqS3Xxqlz9i5PP7QFfXjGKLf7bw,3237
|
|
456
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_HrEta1vlWll_2c0v6RpEIUQirMD1QaOMU81VaJh9Nc,3254
|
|
457
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HvSQqJi8Lb7NBGmvp9YeF8k3nB0t94DJ-LvCX6Spjyk,3255
|
|
458
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=EZV3ffICZEq6X16UNFpHL7kOuV_qmj1L8fJu_F1c-DM,3260
|
|
459
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rKQwdgkictjg9DjBFVzHq9LOMlX_Ul27jllTABjaUtU,3252
|
|
460
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKcB2Ka8jkahKCNF215Ec6rCoy31OrElDL1ZHNgCs3M,3252
|
|
461
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=K1aeYxtOM4niB6auzCEBVudmKIKNzHPjMoFeQt_KD-A,3263
|
|
462
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rtOl3v_tR1iCF-Em0KihtLFzK5qLtndPK-jKCERLbNg,3264
|
|
463
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
|
|
464
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
|
|
465
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=HNvrgcXxV-eVMLwb7zY_R5KgJ7uBz-YIyQsKq1lWnWA,3263
|
|
466
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json",sha256=bHJEVy-CeImiY9JBRCMlHfHPAUi5xO7ENxgVVboN2Yo,3258
|
|
467
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=PnNmKSRFznCIUzZ4ZfaYTrMHeF2_kCQr4_bsEy_9Zu8,3259
|
|
468
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=0Vlxxzp4wrvkFj-NF4OAsJAaPkm-hhisJg0tgNl-W9g,3254
|
|
469
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
|
|
470
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
|
|
471
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fd2p65T9OboKIgw7MQc4IdKaJsoO73Nu3VQiKjV6Ffk,3261
|
|
472
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FUGuYbs_QhqKfErofvbTUplhAVN465A7NR_-ryXvebE,3741
|
|
473
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
474
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
475
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=skSJdv0Pr4rba5ODxp-fHZ6dpxn8KkvACGzNf74j81I,3257
|
|
476
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wMt0NyoRSdACdmS1Qi3qFiu6GiFX-4lVvbGEno1W4zE,3252
|
|
477
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mtm7RgEBEJJkHsOis9BtAFo1OCk3vBbt7l7eumDzd7k,3263
|
|
478
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kfEjBrcwt21QRzimrgY_SQ0syJVJzx0AcWQcKQ3j5sQ,3254
|
|
479
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=R4B2n2vGt4pPo6jS4Bmnx8AYtcfF9qQJE5bD7OhmXHs,3265
|
|
480
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JnqtO0t2HBcQECdYavi18mu9_MwblGr4zfRcW4zU7_c,3265
|
|
481
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
482
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=l8y606GTM4Xnd9CBdhjt7LuA_1KLQS41PInHKNfZAZM,3242
|
|
483
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
|
|
484
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZvsFOizI7EY5V_V5gdjyTgbdJfeKrbxhISxcppSfduo,3255
|
|
485
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=1XFStvhg3yV7cMwJcpbLfaCY2B3nqZNrJgohJn0ma5g,3254
|
|
486
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iXoa10iZi9EQ5jAiMIu3hCemsvjiWVBtn4rKVarVCCA,3256
|
|
487
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BdVjlDZWnX6_rduBTQWfc6Gb4o9z8JRlI5XF00CnJC8,3255
|
|
488
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KPI0AqxGlxtJ18tj-NiFjBleS_ihwmLSt5pg3GXGJ-c,3255
|
|
489
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=S3nHQ7okmQlkuz7gQnHmZWcQQnFDacB4Lz1isbdZ49k,3258
|
|
490
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86ajYfCiq1urzJxcPrvyx884njCMKizCrS6hfx69WPM,3252
|
|
491
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86HDa0gqUZkPaOJLmuax-j-HBC7t5P48NuKMpH5Uj3g,3262
|
|
492
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json",sha256=NBj9yhhUWHpNcvwYhPtBKEn1It7BbrnRMRN6Ji2Iazo,3234
|
|
493
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=7FM4MDavNVOcEOFldsZs5H-E5O6EIAHDY9n-aiLY_Kg,3238
|
|
494
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json",sha256=DaChAo79RafXGjpAOeO1CQ9DazPk7Vazb5bAEyDOYSA,3233
|
|
495
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json",sha256=BB3qPMREaACzWHmhvcETQHLDYGX7GXTKr1E5cm29uC0,3235
|
|
496
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json",sha256=0avMzgfoHRzULbxIdzI1SVCWUSBP10kKvxy-3Mv_y_M,3243
|
|
497
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pnK1HQ2B5ECqCBolRa5Yb4qAClVoJ2pidBnPy3GBLeY,3244
|
|
498
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json",sha256=q5AAAH8gIaU--3mXhSF1VdFTFHNAy5c-gUvYcm9qhEg,3235
|
|
499
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json",sha256=he8rleYTT40kpshJW1FsdiyR0nRU367CqytS-9-UZNs,3243
|
|
500
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json",sha256=LcMD2JddiX488ddRCsh0cXaf3my0VT0IweqQDyTWZwc,3245
|
|
501
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=SyMqNl2wL11cbj95x14YynB4YwyQlaOf1yPPIK0jcJQ,3249
|
|
502
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json",sha256=npr855kvWlHILzi5M0sjYjofPAO9bf6WCF2oZZ4u3to,3236
|
|
503
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json",sha256=xR_v4wy8_ae9fGyuTnhWY0d29NwC9ChPKvdCK5_PS2Y,3244
|
|
504
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json",sha256=femFBZsNptZ6DlQ32dpBu4zhFxaG-kcs4MFPTxipui0,3234
|
|
505
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json",sha256=iVnryOC43Rirq38PwPxzIHrWvf6pA4wHZtf1HOgGtlI,3232
|
|
506
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json",sha256=K1HkIsowgSbvwtAppZZPudYIIni_waoSxDkARTCEQso,3238
|
|
507
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
|
|
508
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
|
|
509
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
|
|
510
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
|
|
511
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sCmfFCa-I5Nft9ap-ScL0PVEKZFibkhtVslbFs_NLQ8,3234
|
|
512
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=KmYAPOgz-2qn2c5lY8u9XRy8i8HNkmOR5m45TIuwt4s,3235
|
|
513
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
|
514
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
|
|
515
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=PaFLbT5ftJiiVSOVkq_DH01EcbIs0sBVkCd9PdYYmw4,3253
|
|
516
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
|
|
517
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=KEN6xt8pgPH_FbLT2fsAD4s03_V-Z9GXuEC4IKe3cPg,3262
|
|
518
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
|
|
519
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=Nm3LPD8JxBYGflI42Cy-xyxZlBLrGvVbnkf9NUmx92U,3250
|
|
520
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=iz4W1UAV1fcz1ZFh4hNQSLJ_F1MdXW-V3msy7t0WrRM,3262
|
|
521
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
|
|
522
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
|
|
523
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=hLFfmEnpHDZlwBlx7TzfxbjCEywqHEuhjllVR7g9yMY,3259
|
|
524
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json",sha256=g3M9w0Noi3DyQB7fcr3jUM62_LKZvTwbY2GtzDGd9_o,3251
|
|
525
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=W1q4PfievvgJ_SiPsDhOsR0Q0eJKb4o8JZhMcVhC-_4,3264
|
|
526
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
|
|
527
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=HJcV-Tzt-yojzNQkPCgi84B44F_RppXxOIicRyg20-U,3264
|
|
528
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
|
|
529
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=9vB_5KLq88zBCNpyz6LE7qAo2eS_sgTNsOh6awGnjT0,3235
|
|
530
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json",sha256=b6lqVlPt68GZ1wlYu3UtC6zkXnnnKwh4tKGltXNvTVY,3235
|
|
531
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
|
532
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
|
|
533
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
|
|
534
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
|
|
535
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
|
|
536
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
|
|
537
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
|
|
538
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=0bH7NZ6VmBBycMus6v7sDXCXtort9awuEpttLLMTZms,3242
|
|
539
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json",sha256=VptbMpckYKHKYMJZS-EaO9G0cSL6nciL9XyeHiZN4Fg,3237
|
|
540
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
|
|
541
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=56iA4xNOSuaGWgz2Qg-NiROhpdoBMto4NVUnisUsyD8,3238
|
|
542
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ICdOnZoM8waiOVeVYP18QiPDSbtg9Q6yO-OrO0-2xtI,3242
|
|
543
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=X8FVPE7rLblDs_Dw_Iu-KDw9H7PaC417EHyVclYjfv8,3733
|
|
544
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
|
|
545
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=CnjQX3SlQn6fIGsX6P_dbNO0TYgAd-sVUb1FfDcDFUo,3732
|
|
546
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
|
|
547
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=V_sgDtEtGEuBsGVa0maYJHhhGqe1NE7l-1ek2ed9WP8,3082
|
|
548
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
|
|
549
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
|
|
550
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
|
|
551
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
|
|
552
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=mVH8Rl4sLATinf7_0A9lTS83kv1E7Cm9oC0BL-pc9n4,3732
|
|
553
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
|
|
554
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
|
|
555
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
|
|
556
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=5exlPUKvZxGDR0UT4_Dn5fp-_ZETJ6_Dbw_Vk1u8bbE,3735
|
|
557
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
|
|
558
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
|
559
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
|
560
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
|
561
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
|
|
562
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
|
|
563
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
|
|
564
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
|
|
565
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
|
|
566
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
|
|
567
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
|
568
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=csHezh0HGWaNwrblGzMgcE95hqbqjWS8HImLRJYr_ts,3266
|
|
569
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
|
570
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BTpwe2RgMbzP9MTtbcJ16I1IAK0ghD0rauWEea8TOKE,3446
|
|
571
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
|
|
572
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
|
|
573
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
|
|
574
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
|
|
575
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
|
|
576
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
|
|
577
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
|
578
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
|
579
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4aK_plqztXcJ-hs5_PsAvM0jclMzcO3hd3zTo0FhDro,3251
|
|
580
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=qqFoMaObuO8pFWcSb9q0wYsdC4eSCO7B-_ruQhR1N9M,3264
|
|
581
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
|
582
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
|
|
583
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
|
|
584
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
|
|
585
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
|
|
586
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
|
|
587
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
|
|
588
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
|
|
589
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
|
590
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=obzfE_9XgsbFNfC9biYOHxR-V_Bgc7PKT8qZZJaiJJc,3262
|
|
591
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
|
592
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
|
|
593
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
|
|
594
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=QsR-Xr9vyuiArMTSo-dX-1DFgATfqwIGOzFuQJAuE_Y,3734
|
|
595
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
|
|
596
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=D3wX0_s_ylo3nLIUfaWZmGYtMvX7oiieOLMdQ9k7mng,3734
|
|
597
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
|
|
598
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
|
599
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-Tj7ImS6ZFDof_0VTyq7kVm8XD9B54RD6CUOPSf3Jjg,3265
|
|
600
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
|
601
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
|
|
602
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
|
|
603
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
|
|
604
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
|
|
605
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
|
|
606
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
|
|
607
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
|
608
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
|
|
609
|
+
vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
|
|
610
|
+
vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
611
|
+
vllm/model_executor/layers/mamba/abstract.py,sha256=J_uJ_CNYQwt9ZkIVENu15xUaydk_tWRdvMGz31ZEnP8,1438
|
|
612
|
+
vllm/model_executor/layers/mamba/linear_attn.py,sha256=bMpTWSB_Nu8w1thzqydPogP46SOxwqbAAAXDL6NDrWU,17268
|
|
613
|
+
vllm/model_executor/layers/mamba/mamba2_metadata.py,sha256=3uYf2NFJN6v_TXh0oqLHllWUpyv6UaXjp_ivoiOxrx4,8167
|
|
614
|
+
vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=n4jGzA9U5QA1CU3DXevsTZW04txbtroRxwOQGKXNOCw,21504
|
|
615
|
+
vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=3pLhDBqw9AlQPKfzYiZ7CblTCfCGjOu6jbKFpb5k9tM,33220
|
|
616
|
+
vllm/model_executor/layers/mamba/mamba_utils.py,sha256=8jf7Vl9kaM40lp66rxxeLNiwJE_7YovjvqyL1lXz0-g,7058
|
|
617
|
+
vllm/model_executor/layers/mamba/short_conv.py,sha256=UODbyqAKqYshpsWe16KJaCzFZ1PFM98C6QPeEMAV4k4,9920
|
|
618
|
+
vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
619
|
+
vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=8jmec0EsOOuNbBfXZZGUp0yhp7GsRlBB0qArv6Garr0,39441
|
|
620
|
+
vllm/model_executor/layers/mamba/ops/layernorm_gated.py,sha256=VT5YCFzEKdUJzwGci9cOxy3JsSaTB_vPrYeNP8GWNrE,6074
|
|
621
|
+
vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=SZv6dt9OlnjU6cOqpU6kxPEbFcqLI1JgF-4vOJGRYLE,14282
|
|
622
|
+
vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=_k43ejVu7CTTVnxNNQPQ8_ByedPi9kUDirJpcD0jzhw,8640
|
|
623
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=0A4kNSYPOuNNL2aIJbKcKUGlZhy-2G_3YtZ1kI7B_io,20392
|
|
624
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=t850GGbq0wMcITXmeBUhKG99DJGjnrmpc7ndZrhJqrc,25684
|
|
625
|
+
vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=28jx7ey1BppmiMwvxTawng2dE0ZPNtK4yroFbPO74RQ,10047
|
|
626
|
+
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=a4BlEV8kiNe5WdoXgxYQE2P2xi4oDLWulp4zIjfld18,10002
|
|
627
|
+
vllm/model_executor/layers/quantization/__init__.py,sha256=WK_AQXb1Cs9ZjDAKH7haT5oOZk4T15__gzrA4P--V6Q,5200
|
|
628
|
+
vllm/model_executor/layers/quantization/auto_round.py,sha256=D-UNGUarIC_TwsHJzmNOWi_BmP8T75Au2BvGFPA6pvA,15288
|
|
629
|
+
vllm/model_executor/layers/quantization/awq.py,sha256=wlzw9mmHYQgKHiz62ATIIgsxgCe0aUJ_ROKJT6riQRA,8967
|
|
630
|
+
vllm/model_executor/layers/quantization/awq_marlin.py,sha256=L7meTTRWYA-8JWKzLbqg2A7pKKT4Cki9t1bupQ12cg8,22688
|
|
631
|
+
vllm/model_executor/layers/quantization/awq_triton.py,sha256=o8Lqo9lLcyhlMANnDc2NHB63lTRutStBxi93KVQMC0U,12484
|
|
632
|
+
vllm/model_executor/layers/quantization/base_config.py,sha256=7bO7WjIwhrM6G1EdnQsxdm0inrg6hu9UXTouvHe3vgU,5772
|
|
633
|
+
vllm/model_executor/layers/quantization/bitblas.py,sha256=xUGZuAcBUAUcNve_afPDJmCFmo5kwGMrvlmFIZkGOPw,17677
|
|
634
|
+
vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=gTdku-PDotlFqoR6-QI89AdwUv6jZCeGMAqxCcD9K_c,23228
|
|
635
|
+
vllm/model_executor/layers/quantization/deepgemm.py,sha256=U3bwO1n71QNRakmizek5YlmDxPkT4q66TALY-DPiB5Q,2266
|
|
636
|
+
vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=9bCs0a9MGMToo0-IXR03U5ZTxrLJPy6vXiz-thiahIA,7346
|
|
637
|
+
vllm/model_executor/layers/quantization/experts_int8.py,sha256=ock48qT0stXtc6PORaDI_wWWpynZIUOSDUU567BX8Zc,8452
|
|
638
|
+
vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=53t0aYukyt9O8j_GARyOUtHRFhXoQsE5tIkHcVX9zOM,6986
|
|
639
|
+
vllm/model_executor/layers/quantization/fp8.py,sha256=xTaA4plgqzkSlOedgtcupMOWMVCHBIsDgkSo_dQiy0A,55570
|
|
640
|
+
vllm/model_executor/layers/quantization/gguf.py,sha256=OEQsWqBT8iTR5pqJykGFKN3SY5wmiD6U7Tu7OMDaM7Y,22592
|
|
641
|
+
vllm/model_executor/layers/quantization/gptq.py,sha256=R5WxmTXyLjj3XTQRZsGIzZiwFvX9RzqYwctYlDGQmTU,11798
|
|
642
|
+
vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=M8PcwO5s-jzXYzbpCEsayaEvkObahNvZ0OyeiXdKWOg,17132
|
|
643
|
+
vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=CPkMcgpc55CbiGCl7e_bmf9GX4oSkbzIwqJS59S_NrE,28112
|
|
644
|
+
vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=f72YUgTT0ijIZoALWx4wn6M0L8aYpZxxKrb-cRWmZKU,11018
|
|
645
|
+
vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=VJJ9BPxOfO2tYT9xKE7J6MVS1YelQtvA6pGdbs0eDD4,13012
|
|
646
|
+
vllm/model_executor/layers/quantization/inc.py,sha256=Ye2xP-vg0fK1t4QwWHP7pzelKuK08tyKl2BeFB0LeH0,2300
|
|
647
|
+
vllm/model_executor/layers/quantization/input_quant_fp8.py,sha256=u2YwFJIef6oRV-CLE7DiFyLwsBWImNq5WpIDXp2x9mw,4067
|
|
648
|
+
vllm/model_executor/layers/quantization/ipex_quant.py,sha256=ArQzoNGlTWtMZKz3LBKCFp5pQMGHCfS9Xx26pjvrMmE,16978
|
|
649
|
+
vllm/model_executor/layers/quantization/kv_cache.py,sha256=8e7uCDHW4rPO27FvzNeN5yk46jNSXgRse8lCzYQkTgM,6226
|
|
650
|
+
vllm/model_executor/layers/quantization/modelopt.py,sha256=MzMk4of41OQeDGNXlop67nhcD1o4vH71OgFTuesFMDg,67084
|
|
651
|
+
vllm/model_executor/layers/quantization/moe_wna16.py,sha256=4jQfHJNDd5GcgxR_qM8kgeMUH3uDGAKjfzKOVg2eedQ,21112
|
|
652
|
+
vllm/model_executor/layers/quantization/mxfp4.py,sha256=-zMx1rc00-B5VRoelPTihcQg5_0Fk_zMV4ZayKsvjUU,42755
|
|
653
|
+
vllm/model_executor/layers/quantization/petit.py,sha256=Ef9_0u3Rt9G2lYZOaYCGBMI_li1tud_LoMJsVgTEclo,11719
|
|
654
|
+
vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=0PQY-cMiMcKvB9bUENLneP_egRdGwPyRQCtzR-_p7Fc,5452
|
|
655
|
+
vllm/model_executor/layers/quantization/rtn.py,sha256=jFd9hJJBScxwH9F43m1UnutLY6la9b0DTTTp4H3_uhA,16556
|
|
656
|
+
vllm/model_executor/layers/quantization/schema.py,sha256=x7y16hNaValmG7etgyK0RwpeBCPapT1_GznqWBQ5kGg,3749
|
|
657
|
+
vllm/model_executor/layers/quantization/torchao.py,sha256=682-CVQJ3SnwHUiScqX-GP65RfbMO64h5FypoqlAbIA,7692
|
|
658
|
+
vllm/model_executor/layers/quantization/tpu_int8.py,sha256=otNiEBTZm5XFlkeLfNjPF3CMG0QR5u0U8AQy-BL59Kk,4795
|
|
659
|
+
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
660
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EwYEsC5H8YLJKRUZvPa9YbGNAn-t-r6sDtqI6E4xUEc,35579
|
|
661
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=EhZXHH79SHoHK0GIuVQG5hSuh-c01zjgdJ-uLk_zYPU,71735
|
|
662
|
+
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=nbbIQHQ0e7RzGJKHz6j4BeHtV_pFO5ewl1_jjaI9zRo,7851
|
|
663
|
+
vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=cBduNYE8ud9bePaFyzAZ6dbUz_kztBcs2qsvSIYShQw,7854
|
|
664
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=EGvkXV4Hm2DiyS_NqQZi_35do7oqGTLfbDYjnRLHaeI,1391
|
|
665
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=NlMyJIAZgOIgSgMGDLZNV1kC4bAtk6TCcukTVJUCkjI,14500
|
|
666
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=phymTDNBBnHfLXhq9vmwklinzKDZKdYrfp59en2VOok,1596
|
|
667
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=002voQj76mVNI3xF3d3IDmI5LM3-_eGXs7VJOarOWuU,6270
|
|
668
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=Lgr2COqF2sCxUTnwlBu-P9J9N01aNlf0fqFL8y_d3U0,4649
|
|
669
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=Ex6j4Mzah1mzFi3gh43D1hu-wUJTBbiILV3in9aomFs,6823
|
|
670
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py,sha256=5C2bhbprusbPVykruQy7EuB06Rzxla0i_-x3awZWH3g,7152
|
|
671
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py,sha256=SF6TWUoz3TYVncl5BTVeIhpLAqDkbVFjk6R3uUvsgKg,5573
|
|
672
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=Z1-7Bh_1qTwnKkbbj2xO1zn19O76iU-uLWRZwdH08QA,5491
|
|
673
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=F_d_AYnbpml5KBvqqiO60Jgp5rzfujEjBFQOZmvQfWU,6801
|
|
674
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=TpqBbRB2j5Jbvo4Gczvjy4vqlIEP-j8fljl_nQ66UtI,4930
|
|
675
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=tmixOaeebRl-bVTUwRwZMlqr-vhBXE6BeixzhzAqCdg,8541
|
|
676
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py,sha256=E0javw3ADH-RoVg6q04k0FlI67S248nRQjYerDbdAFA,9524
|
|
677
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py,sha256=GlIeFnCPkBWLIU129G4S61fLJDE8qQqNzQCI1Kg4nuQ,5440
|
|
678
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py,sha256=zOt-O0AsZ978entPoKuAqg2gzEgMVK5FmW14GVBLfso,349
|
|
679
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py,sha256=BlQrGY0b51M8u1cZOIDOVUdSlGHizEx8EGd-jUINfZk,842
|
|
680
|
+
vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
681
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=DCfiQO0bOUfpuAp5z_sdu4B1agRfbCvtKTZQDn8wC7M,2984
|
|
682
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=oMHyhFIyt70Osib76WlW7Sv5rhdOGOLTG6t9VjvTuWo,3760
|
|
683
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=feWdTXJ4hDpJjQEIQhabjfyZs56JVY-uza8UD81i5MA,4444
|
|
684
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=uoVMlDWnlsv27rsrlhguwnXJ2hA-vNRsKGhGcOKCIQU,12117
|
|
685
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py,sha256=4FApYttHzs4eM9QPmuzSbM3uqtOqvsayctk8bi9AEl4,3329
|
|
686
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py,sha256=GdkuG0t-O4n0eOT6FduCUnqVr3b5H-OMRpmENK2xZ8A,4508
|
|
687
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py,sha256=cjvAg-jeIUYP9ZfDTVdOzpw3sP7Adi7pFs2B5sy7n4k,3794
|
|
688
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=rKbWF_TyxXjbkm_a28tge9GhOowg121HECmWJIIAm-o,6213
|
|
689
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=1uYA__lRJv7g8L9OiHUttOHqX4mjGRVR7GDbG4yZgnM,6194
|
|
690
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=L2h7Lt-5u611NpqhMVjP2a5J1IanYdcqtScF80-s6GU,6130
|
|
691
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=0cL2WbqxsGFMJMlg4AgAt5_EDOncrIB2z3vlg6FoOk8,2108
|
|
692
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=VR6lep_0vVQcxg1CZ86q1K-ekAy26behEGO1VL5_Cc8,3608
|
|
693
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=oSbmI2opXYqvcGdcSPDOH2SHVh0FQm__wCL8q2kOii8,6072
|
|
694
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py,sha256=Og_Fw6Sxlbqnzjhhk6hYcUNe2WdiG7gzESp6YAVIhhY,8141
|
|
695
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=ShCi8lhNicAqCuMQzxotER04YFowxqUAHX6XSeqTmBQ,6021
|
|
696
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=CgQydI5ERFdaOzOJNR5SPTYIkAUDI-pWr8BqydEB46A,1345
|
|
697
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py,sha256=81LnTkHDJLJ4Yu2nZPVAYq1bFXtzBqIgH0ok97zuuBc,4040
|
|
698
|
+
vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
699
|
+
vllm/model_executor/layers/quantization/quark/quark.py,sha256=owGXt4xXGXdml6ROQ3f9SeIWBerH6_JEr3Z_LBsOUpc,18499
|
|
700
|
+
vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=t6Si_b0Ib5bwQYwgpP0bSE2OqjLgeu0z690PsKI9r68,18389
|
|
701
|
+
vllm/model_executor/layers/quantization/quark/utils.py,sha256=Y1MHt_RTfPOCSb7_kQHK2CQZCaQvG1A6mMA9s70vbDQ,3658
|
|
702
|
+
vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=TvlHrwGTaJp9nBDtUl4n5xtuuPCR18XQVyYGa11AdMM,353
|
|
703
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=YkvgTw1sECoubOhGXMixFd47StURg3bzGiYsur_izzg,1560
|
|
704
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=XdHk59N1ibw5rQhX_5MBVbf9qOLYasAcywAvV8Jksak,4210
|
|
705
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=s2L9TRTV1J8FQVAXpSUwH2Vjo29dYV-kQwLYOBNN8PU,7222
|
|
706
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=TAZaMWM1lydY9bxKj-mdzRbMcUhSVTIPXvUmt8vll0I,5462
|
|
707
|
+
vllm/model_executor/layers/quantization/utils/__init__.py,sha256=k9dh5aEvZi-6ECfjG_Jq2iijwEfjmdRA9fcHjG9uKd8,235
|
|
708
|
+
vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=ejjOMJ4V0UhgYiSvYJf5_x6zJA5iQkAYtzLqaw2AuXE,2260
|
|
709
|
+
vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=p7A4Wa0OyHl34fJKUvy-hUH310Y2oZrouEE6wSz7f-c,8290
|
|
710
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py,sha256=zOkv_4FIPNcFAvowOx0m1tZG44t_HHIH-6budkcMyQM,3230
|
|
711
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_utils.py,sha256=04lcyZ8tRop6mCCCs2RRN6scl_aS4gqqH7x3gVQDcDY,9979
|
|
712
|
+
vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=21odwHVbcPoAWBD3qlEA75FJyiTj3y2ubOzrrG7dBrw,27167
|
|
713
|
+
vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=uqm76R5WoKJvvHFPct_trYteq6VyrfoA9qaAx1ighA0,3913
|
|
714
|
+
vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=s7yNnvetxp3E0vJkMoqluzg_8AgxDYi0gLGISj2cUGc,15420
|
|
715
|
+
vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=KwNOkW1XYBIOjb8UJgyEKd6T_chNqE_YVskWMtrOmyo,1631
|
|
716
|
+
vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=1lvRUPFOjZj_wNl5XMTxntf_sM_J1KS-8WFj4vFxeRQ,1658
|
|
717
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=YKpWRCQ1nZ1n3w4gupURf6wLgFaCzxPiNI_Bnwq9O-s,19199
|
|
718
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=Mz8-V7C-qqGAdTGjbDatQECVlbyg5Cahmbuxx0shXO8,15507
|
|
719
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=J5FjdJQ5PERg6zZ7Wl7O0op4IKjiK40RvMQbrgw9J8w,13880
|
|
720
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=GtmzVpQhQCQ8-ajEADNfzUhZW_Ph0GWs0VoSx8QJJ-o,5374
|
|
721
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=3_204vZjqNj1Em7VxymB0CfK3TpoHpaS0xY0p29WyDY,17603
|
|
722
|
+
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=UEQK330QlIeKtAwdKzy-tFY2yUjhhBJ6X76NNRcFAVA,5402
|
|
723
|
+
vllm/model_executor/layers/quantization/utils/mxfp8_utils.py,sha256=5_KEE10L4lxpjZ0DuIh1JA7weu5Me3aLQt0tyf-5NR4,621
|
|
724
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=SnaxN2W5uooX9ug8_GuRERhoj61_3XpoJh3h2_pO66Y,4846
|
|
725
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py,sha256=2F5j7BbMir6tZ61pmbW-Mxwj0tIjAOBwsW6jblDRdnk,1990
|
|
726
|
+
vllm/model_executor/layers/quantization/utils/petit_utils.py,sha256=XhbU70TgTv8iBHfv3YoSrRZIF54ueKDMRsH28BeJb4Q,4186
|
|
727
|
+
vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=5FzfUyW4IUVwKULpBltYrjf1iOCkZXGvBJ5MojkiEZ8,21045
|
|
728
|
+
vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=9BHIvAQkaSoiy8g31H8q48JVaAb4gbf7BiarXjUm5w0,18951
|
|
729
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Szg1W2xH7h5U-UOH8vHbDV_xs1xO3AM_wITHbJtITgU,3264
|
|
730
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ta8XgWb_aVhJwqJ59i1zzY45NhCGazJ75whDUmOfyVw,3259
|
|
731
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=t8TaODfMF2Nq0qg6KOc8NSTs7m90Jcu6Ih3BXUvFb04,3799
|
|
732
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
|
|
733
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
|
|
734
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=-j7Xyk4xFaiAD90FeH4AqRSnS82f4owKRGMHbObrrHQ,3250
|
|
735
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sW_T-BdLbjJoFqlr-B5f9emF8E0IdKfy_1wUSIEi55g,3253
|
|
736
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
|
737
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=akDNAjUZ3EXBznF9w6qUcpXxaLWq7oXnX5jy-R9cleI,3246
|
|
738
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JAycl7EaUZtmCoXMjq4JwKXCeXxZ6S4Ts_DricRUw_o,549
|
|
739
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=q5KZyi9T-l07P3r1u9i6-Dpw89Upjw1gpTp3f1CluEo,3799
|
|
740
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
|
|
741
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
|
|
742
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DLCfW5tQ9k74AGZ2yER1etP-HgUGglPp_woJiaPuxgQ,3249
|
|
743
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8v9mdWPs1eXczo3iwFrNnRo2LF9wPU4Scm-r9bL7Fz8,3251
|
|
744
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Qoj9rLLRDbKM4IKBCXvN8RcxzSmNPd0TQUiM7CXDqHI,3241
|
|
745
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7OFCbBqqEA7vQ1oiygfW-7Tqqx8OJATaLujtcQIgyTU,3247
|
|
746
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4D3Ku4y7BCVEJzueKvQC_KvOR026w3ONWsxfsA_YrEc,3249
|
|
747
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iJZ_tAzoYGUmg9ltil4e8vzKlKi980yTmswEMWqV1Jw,546
|
|
748
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fDomA7uBQKX8kbO_4MFcoBwHhIR_7sOkngQPv6cQq4Y,548
|
|
749
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ucrZBIN_ivmmfMAvkT40xQpH87LdQK38lZbeLWMyV4M,3806
|
|
750
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
|
|
751
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
|
|
752
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=zd5cMYrxQ6PD0jKpd3YF6ThT9RGdqgEQnCW6F4W-r4E,3249
|
|
753
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CjO6dh_qt1iTu5kYRs98tTLL-W6FOzLO4AESMUFHz5s,3254
|
|
754
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7v4tp0RaT4vxF4urSBrkK5FR_5ikeFQ1htF3DwDl1lk,3249
|
|
755
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M5F5wzSmFokEm0X8__ogLvdE1QVC6EW8atqq-kp3rVA,3253
|
|
756
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0J2MFgaLkv-mfVE5x363lgVKYU6miLG_xRO3tJUga_M,3249
|
|
757
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=983yfFeeo-BClL_H1g-owXwbA6t0l-kREiy7kLURUMw,550
|
|
758
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzrnY_xKo39wZ4nO8zUorLp1ivTFabB8ZQOFRx5JcMc,3251
|
|
759
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=f7upf6kaHS5_3EqQYDxtSsbgb4D1iTvjCiC4auzbx3Q,3254
|
|
760
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=C2eM8RudmP-qXEf_Apg-qcB5n2Ugxf8-7uG8hQDSt1g,3801
|
|
761
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
|
|
762
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
|
|
763
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=q9HUcoL0cdZCOWZ8MKbcpR8NSy5iNEBq6NPTaHLgRB0,3242
|
|
764
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=uJu6Gv4e80vxVrDyBo8_y47tOV03RmWVsMIWQ-bbW6Q,3251
|
|
765
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4ubbhwSFX_XbefRLEkLoWxJkcetFWPzsszPu0X3_Wrw,3242
|
|
766
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=euiKvhb3DXkvPPQJLqNE_xN2evsTOoZnVIiquyN2Cm4,3246
|
|
767
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FhyniGTx5QeCuVrBSVTQys6q05Pr5lPEcPykpAX7Iyo,3247
|
|
768
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pLQvMaVvlet_JenEz25mxxplAaHNisl6SFTSZ7lYP2w,548
|
|
769
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=irQUBLd3KHNd8JNX8eFe2fBB3ZZ3zMl3aAF22uxJ65Q,3266
|
|
770
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=gklD55iBvg488-PecvtcEypwCDZ2lCi8c5o9bqgEEeI,3266
|
|
771
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=uAa-ZQmASwlqZbr1l1CM6FyJI9irNdLBzc1U5Hdyw1E,3802
|
|
772
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
|
|
773
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
|
|
774
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=cE3BscS_zEtF_m_jr51IPfpaZZgIEojmhTHsrb9jABM,3260
|
|
775
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=SScyo-oYCBxJR9C7ZIKu_pJJNiXdpT13kYe26rddvPQ,3261
|
|
776
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0v17v78pETXv6S2ZoibekxOVhiTmCm807DYG4DONUck,3259
|
|
777
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOuovUsPAHqZlbr4G3_CnCNE__fgxCz6RuOhOxCwWv4,3258
|
|
778
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ulvOEAFO8c-UOa34FEZrjOkCR6ovhJlfFFDhmaKIBiU,3245
|
|
779
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=BiZowqExbvXftuE37SYcheOdtYX7Z5BEXyykJ6GbYSk,3254
|
|
780
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W-xd0c2ziC5YbC96TXlc0xkj2cmbfcdXclW453PsLpI,3258
|
|
781
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7ok0uooTihvRSckZMNd6jInRvht_xkC5posHO66ejqc,552
|
|
782
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h_Z6wBKdSGBEo5BfQKaxuFlxztrnbbZR0pkcYKv92sk,551
|
|
783
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k63VgniyN3Rl_-h1hYmT_q9QZtSFqQmXBqhEXJQkxqE,3800
|
|
784
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
|
|
785
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
|
|
786
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sL0E4zZzb01g6GHaTCXltg20uSbthXHSJFQ0SaxZ7PU,3245
|
|
787
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=MZcJz7BjwVOHHHxvYqGrWw77WnxslYhwW80bZw-jSKQ,3249
|
|
788
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GsLoYkaZ2p4Qu0Coj-X90s7JWyfZBOloIHPlyNKSIes,3246
|
|
789
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
|
|
790
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=NjEA2QjOVXyOaVSMPch5qa1Dq3igbW7MmE986-7taW0,547
|
|
791
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=21Buh2aiGTHjpW45Rm-TwZD8MSaAy8NMUrK5l_hGT5k,3803
|
|
792
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
|
|
793
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
|
|
794
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=8zuJhFdd6aXREpiqPFhIKEFWA5lgLVGrG0-a9UXcBqk,3262
|
|
795
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=_42bDZX4VODErI6OL-NrWja36iNHC4DzgF1l5Mk67-c,3248
|
|
796
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Zn1TvhAoPOv0zQBYHOZhwdDw3oqyxm0zIa7IJkTCHpo,3247
|
|
797
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
|
|
798
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2T2TYZhXgC97slH92HQ8GvZS3KuUt1ZiC3RtudPVEPA,3802
|
|
799
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
|
|
800
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
|
|
801
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=yqjO7zML7EseBJw6Bn5MTyHeAitkPsl1dndXeL6Rn6A,3257
|
|
802
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-nQIhKAOVCQrxLV6HDlcD0V8HMWvqrv-vyiORVU7qls,3244
|
|
803
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=KKmCvNh5T_qfD8v7JijMqXxQ5L6-gRX7oc6c5re6EF0,3248
|
|
804
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M3nwpZd2-0w263ywZt9gaw53z7MN673T5tl4tc43Ntk,3249
|
|
805
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
|
|
806
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KmEgJ7zP2Sr_7GsAfL-12_g2S2a2wVpnxgCiF5dFiLI,3802
|
|
807
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
|
|
808
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
|
|
809
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=UjBOmVqYynBH3dJVuMJXjKnuZ6LssohzzEBpLBG4_G4,3256
|
|
810
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8BJsjc2UUYdotrIqwyzisjrq0wcyW4jnTo_M8J3qYwA,3263
|
|
811
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vLoV3JMtvHOKpR5D1BeCQPMuYlWUAlrXu54gByNkwKY,3266
|
|
812
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BmXTZvWk7kphfBmGmuSIuolAK-3qCGdmcPhD4FcKd3g,3265
|
|
813
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=N0kCPHvybNK-HvMO2EqNDLkj7m7WrHTl-3AD32LBD4k,3248
|
|
814
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mjh-AgJN_IoWAc1uwhUiB1lE3ufAPDf-KPP6vUTrDKw,3251
|
|
815
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h0qz-pNlC9ZGNbyeFsESFdowFPfTTK3rh8SK4NH2Css,3259
|
|
816
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=mcF12eQTtGxocrVIA3I98NHd1NLd0-8EyfXtqDgv0PM,549
|
|
817
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AThoa7FUcGdNXYB_v9iMpBh2X8C0iLfc7y-C0xy2cRY,548
|
|
818
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MJgIvZHf01ju8IWEVO6vyMedy5OTZxDpzv6A7_8W-Tg,3813
|
|
819
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
|
|
820
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
|
|
821
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=T60CKtM9YhIEZs8F9Lljrdqqc4ReloR7Xl9IYsfex-E,3261
|
|
822
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kk8WqNCGmjh8-tOMHBP8sv_5fW81Xkdzdf8-2WDm0RQ,3263
|
|
823
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cPtr1UJq_B-dTqgMrVm8ptiYXA6qOy_F8rs2f7ljuEI,3811
|
|
824
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
|
|
825
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
|
|
826
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Z7kIa14RjVq3ek_C15q5mUu1IrY2r0OP8S-_pm-MYU,3252
|
|
827
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=r63SZkUJJV87B00hAX074_uaC7wwQXdurlJsB1jUA0I,3254
|
|
828
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hL3doX7zzxld3UcS8p9ACSadDaE6t3xXlYwM7X3GOeI,3252
|
|
829
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xBhxdCFf3waTUsLxJxA54R90zODbC_DKI3XXBVKjKRw,3252
|
|
830
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2ks7TQUULAD-Zn5i69YHo_2hpmsmxlocdYmJccSh2No,552
|
|
831
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zm2eqlVlPWlP-5o944QL40OCzMpUHGkPJwduy8HOV8A,3259
|
|
832
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Yfg4GDiXIYLyzL-334YirvDbcChz-Ep_atCghEZSntU,3257
|
|
833
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=eiI8X2fFNknJmiT0uHbzSaEKQwwZk5bxn676gNvcyg0,3802
|
|
834
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
|
|
835
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
|
|
836
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=O_SV2vo_oaABfT6Mxqcmo12pnhKtfX4TnXfe02OcHJk,3254
|
|
837
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=g12Xkurat7oUS7LdS9pHLKFlur4_FaMGiGBvdq-iBCs,3242
|
|
838
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=EWLxbWncwGJyL-dV6EO-s8kk25wfYrESa0STjCnzD64,3244
|
|
839
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tFdrY5nADmXUlShdN8w8Jzkxuj_RPLXCRceX9FhQ35E,3251
|
|
840
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M-ewEHbgHLBLYLi1Hgz5Pp4kypnUiCRo0ut2scNnvDw,550
|
|
841
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zTzLbdff09HwMuWlWpoAIgQZ6NEjsFXSF0Y5z4Be7Ig,3802
|
|
842
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
|
|
843
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
|
|
844
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TO2qRGmp37v53Zqu8Joeq_BSbtwM_mpVoozGyoNg0-o,3254
|
|
845
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=QqijmgLqIoBUxRPnuUQGsoQASRFRMsCVQKTjEjGecVo,3247
|
|
846
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0xquf00fgfrDODpaxyre0VDcjqfzqExj939rzeJ8pMo,3244
|
|
847
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ipg8iK8w2ySRe1Z08YJUWAHX43rvkrXpR6svxRhSnFE,548
|
|
848
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-wuzdNXf3K0jfFQGB8nFSyoSZ4BfAvIkY10k6FdjnLY,3800
|
|
849
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
|
|
850
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
|
|
851
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DbemSQdo2h5vGjSNB6Fovnn-aAGfjti04Bp-5KxLALk,3246
|
|
852
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=6glWpljtfiuspJv_Esg_LWCDDQ57d2HETsOIv0zr2Ec,3249
|
|
853
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qG6v3n3qF6LE2DdGT-mDIXecZ1a7vg7p3QqXYCMX85k,3254
|
|
854
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=l-9r2k1gcKB8UXlBXVuzkoa1JDLgJVTBQ_OaQK80z-k,3252
|
|
855
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
|
|
856
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZfPPlx0qcuR4WjaFAE-W1QZgSPAMf3NyGcpvQIvyFMs,3245
|
|
857
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9w-sicV97vSQxkRcEKnFKFjkzBOx-VOHlrh6b1hhQ1g,3254
|
|
858
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QgSlDAhlB2W4bzTd2O98UL-C_IKfJm_cVmQz8FqsLF0,361
|
|
859
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i3wy_CBO7BQQVhKReRC2F0PaRIQDdN9F5lJ7kD0xe1I,548
|
|
860
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QpkqpJnyjuHH8Zo4U4QZgehUF2F2uQDZFb8fdhixXWI,3794
|
|
861
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
|
|
862
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
|
|
863
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=RRMNeM_qiHvlUTOAeqwgs7ukSoAZSlK8XN4z8hgWl0k,3258
|
|
864
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=brB0-FFr-Sv2bdrz4DQJ_NaFhETctf1g4Yzwj_Fcczc,3251
|
|
865
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bPQWtvaJrzOOIgI-R-MIxs_f4yC_FobkDydu3OkOFtg,3252
|
|
866
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RYLh-Uim9U2_djLkFwwpV0rNQHik0tZHzecuj1_hPLw,3248
|
|
867
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZRgiuHZ2SFC6u-WV5DGwau4k1RiPLI67eENO0e-5Ylg,3253
|
|
868
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4EzbnLWHVwrjyKYPMcDxbxM2o-krjlT0YXvM8oPH5Cg,549
|
|
869
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OFgOtRkUHwyOT7Hk_BQft_WzuZOwbhMSLP65Fbr4goA,3799
|
|
870
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
|
|
871
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
|
|
872
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=qzmFm2pqxphir1LBrycDZp5JA4It8OdQeQ5iTrTwLNE,3253
|
|
873
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=2UyOMRMdbvHt6WlZdOKALm3Or0eMCx7vvwgLiCYyoOs,3259
|
|
874
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-hP_P8NM0K04mGzTmpGBNibQ5xxh5gPz5WtoMXhoz1E,3253
|
|
875
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vEU4_YOMnLdYFf1BkBEdFbGRMG8KLhsO_t0gv7vaO4Y,3244
|
|
876
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FB5Le4obvPoCgFSnC_3-Uh59n-Mt4Rol8saXVcK3RPw,3252
|
|
877
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k1rzpgm9m19AHf_HPQcNCuSBtAwFgMePUYB1jZeFyYY,549
|
|
878
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9IbzTwLRgTCfFLSvjEWKiajCjG81R-wTljIV2zUYUA8,3809
|
|
879
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
|
|
880
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
|
|
881
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZTPWtJA3JBL2jhy7C60RdsntKCN8oQ-DDIL17ok7OB4,3257
|
|
882
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mokCWoXdKi8p4mLYqgljjwDRJWK5I2oF6_MJuObi5sU,3254
|
|
883
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kLviGvVngpgOuelfKtvv9Is7MWQ89rGxlomMRP6t0Ic,3250
|
|
884
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bIVRtaaHThozH54VIte0Nk0sOGV67K4s2YZUE6QWx2s,3252
|
|
885
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_YXzQ6N3QpF3Ou1Fy-51YyL-J3i5gOBVCgSM42vOT9I,549
|
|
886
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=csaz7AaVDTvCuzaptN-e8K1PNuIwZm9OwnPSJydHI90,3803
|
|
887
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
|
|
888
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
|
|
889
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CE1wRLyFONo4_icKO8fcTTX-5giKNJ9_1F-2mr-lGQU,3257
|
|
890
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=JdUaLiMmf8oEbwuhPHMIncvWzXS2SxOEgfM80ZjM7l0,3259
|
|
891
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vlys0Zi_CaaU41OHGbWSBtbVglFi98bgqEySBMc9Sdg,3258
|
|
892
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-sqiMkGGMzhrs1WdhEfwiNZd2r-NmhEsfvJxczLZJ-g,3258
|
|
893
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GY9VBPi21K6vJlF1NOEzCyqMS7LX3xq5dRxrK0jvIHk,3244
|
|
894
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8LWF55ZPjrOY_sEdRGqf1eLcTNySgUiiWNWsN4EGxLY,3247
|
|
895
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xEN9qWPikXf4njuYyKQJVW0SM5cDReje-euoWbr64WE,3258
|
|
896
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
|
|
897
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZSHvdnC2vOXI2HPW1iNI9HdihoLcNYlRLMF85pqjWZE,551
|
|
898
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=SkyMLsoxGoHdO4kgTerihone7eEi0nmHlrvZUI1I_V4,3804
|
|
899
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
|
|
900
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
|
|
901
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xbDfUYLphVtZWJojZWODlxGMCoiIgxn4LsnD9ge3r9A,3257
|
|
902
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hqh8TQw3t5hPM9u7rmHPuaMjwgxmQ-Zt35fSTgOS0HQ,3261
|
|
903
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ggy4hejkcWjiw5Bi-wGzSP5JLVuvOjip_rbjXFBJZbs,3257
|
|
904
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzkrUzR_nzxnD4L2jF0_8aDX-nidn6AjhVXlJK50VyY,3259
|
|
905
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKG9hmaxN_7tCB_06L1dh0csxs3TGeya9B-X6W-tNhg,3245
|
|
906
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=jb7vGi1RJefImkT3BZU_9iOkiCulcd5oDjxpVSt7big,3246
|
|
907
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=at0_Rcc0-lSzI9MFj-TjnjyDt0HckCZYAZ19q-7p5zI,3257
|
|
908
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
|
|
909
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TWpzs48j0QwApAsBWt3iIlu6cqR46Meslyp96MOANcc,551
|
|
910
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i5b52A1Oe8kCdPrPLBGud7OMHm8779JD0rBocYO_lo4,3797
|
|
911
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
|
|
912
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
|
|
913
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uWiQMh3cZY_EtLA0a3PU8Z1VCunF2PpolTPYeP9Rjo,3256
|
|
914
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OgXOVvRKqsgzlJwjHNxNCsJ_o3POBFigwCqafbh_aKc,3258
|
|
915
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=toHzCprq0KetQI0-9IrLYCIm1bQ0nSeP1gXArU0GogI,3245
|
|
916
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_0V6CEfYgBsaUnF5DwNWWseo8N1Ph_R0la_XN8HzcuM,3259
|
|
917
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pGZZj_gZms1T9Zgjs4tbIm90LhbEy1UUkkgrto9jPts,551
|
|
918
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fqnjZCn0gbY7fO9JwZOHMYJJHe8gceWhWCZOFPRUlYM,3802
|
|
919
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
|
|
920
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
|
|
921
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=LdtOyXsA9r18GiFkmDOkiRinsDSZBZ8NYapL59EZ4iM,3264
|
|
922
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=07GarBHmiiYkyqn-qxEtrAcgCETuUbqm6HqlbH9yJi8,3252
|
|
923
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xMNxtLL_8tyg4TWSt_llz_IJ2qlxc2NEwhUzhV1VsG8,3252
|
|
924
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kEuvCsW3YNByF-DALYqPZpW3TL8ZbtQ5gUNq7-8YvZ4,3252
|
|
925
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uNqB71a6ctZ-c4tF3r66vOsHFrqcR28g_UWy0N8iBo,550
|
|
926
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QkrfZ69jxW_mweigtHL5R0Sv_WcSBp7wjFX75G9kbHw,3805
|
|
927
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
|
|
928
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
|
|
929
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
|
930
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=iu8M35YR-RDpKWbjXSRzk02sW9nr_dtbhalfLSNtxNs,3251
|
|
931
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
|
932
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=41m0bvskFUzVtlr_yppBr4PZ0cVkqHvy9Hrc5pUCUyY,552
|
|
933
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2VxMGfWtxTzXcF0bP3d5s7rc1cKb5TNBAn-WiCKAngw,3804
|
|
934
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
|
|
935
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
|
|
936
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W3cYFteFIZLu5c1K41cOh4_-WZzFU6-jGnZocDzmKaA,3796
|
|
937
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
|
|
938
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
|
|
939
|
+
vllm/model_executor/layers/quantization/utils/configs/README.md,sha256=kfjjurECwd-xH4EDjuueS0Xezi86c_pYu2yELgiw8Ew,102
|
|
940
|
+
vllm/model_executor/layers/rotary_embedding/__init__.py,sha256=3XJWag3s2Cdc4GD5i9FmbXsHuAwuuQY0N4PEhs3ORYk,8689
|
|
941
|
+
vllm/model_executor/layers/rotary_embedding/base.py,sha256=aZhqygUAsvFw2FZ6zgS1TLw9LcD16Kud4FJCRJRe0Qg,6527
|
|
942
|
+
vllm/model_executor/layers/rotary_embedding/common.py,sha256=zPoBs9sCxbeJGAlDWYCeVAZSR5tfOQ8zNX_dXN-9cOo,3299
|
|
943
|
+
vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py,sha256=hAjyjFUWltF6SIRCM06JVeEy-vLMjdc-ATJ4wGLd9yg,5401
|
|
944
|
+
vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py,sha256=QlsW1NxIUKS4F9xpYJXqh163BqRnKO9P_YaaLsewa68,8562
|
|
945
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py,sha256=NmdcYm_hogzvcboo1hgu021DqDZmK41PvkPUwnhccSY,1316
|
|
946
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py,sha256=if7N5noDPXCfKo4nsy4xGs-pyANctGCXp7StSIQqgMA,2714
|
|
947
|
+
vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py,sha256=vAJYBkHhfM8c2ATaDkS9PXFJyuvoWGxEB4q8rJyJlBE,3280
|
|
948
|
+
vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py,sha256=bnM9AVzJE79EoUMqXd8LG-dyfIOITDLp9DEO1Kk8WEA,4677
|
|
949
|
+
vllm/model_executor/layers/rotary_embedding/llama3_rope.py,sha256=W57lR5Ysnnk8hbSxtrGj6rM08nA9zkXiqPqmC0aK66s,1798
|
|
950
|
+
vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py,sha256=x7ar-pGOR0JDuaKVT9G2hvWi0coTDPPbbCXoK3bLn8M,3167
|
|
951
|
+
vllm/model_executor/layers/rotary_embedding/mrope.py,sha256=qZ1lzm6SRZKzugbyqXfeEUDykWNiFZtApB5Gjq3Ctyg,48090
|
|
952
|
+
vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py,sha256=mtAMpJFecIkAHIq9mhHDNuo2FrdrRVWt724yWde_F40,1546
|
|
953
|
+
vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py,sha256=pFfzb2nW6S2KcwP5t6ONQXTQqtAv7tCysYaEMPI4r9Q,4727
|
|
954
|
+
vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py,sha256=Gvj17F4m12WxJ8DG-vLavmQyGKMx7WYTIjiwLcSFqUk,2662
|
|
955
|
+
vllm/model_executor/layers/shared_fused_moe/__init__.py,sha256=b3NSsmahdIdHBmu24qp1xTq_QvXPE5uN7C49OC2b5ek,232
|
|
956
|
+
vllm/model_executor/layers/shared_fused_moe/shared_fused_moe.py,sha256=0KI0seYhUNqYNH15p_siLdW_CHYc2hec6P6OYI8VmH0,1936
|
|
957
|
+
vllm/model_executor/model_loader/__init__.py,sha256=D_j1yd1s84kp2bi9lJQI8NShjMalHp7d7azhzL1qT_U,4823
|
|
958
|
+
vllm/model_executor/model_loader/base_loader.py,sha256=i324mXF1ZbyqS9bp2iJwksnv30AbdCE4I_NarDvhF_Y,2065
|
|
959
|
+
vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=VvUbna_jeMB0Ab0oOp-8O4wkPVoQjmKo2NwzVNxAsCA,35488
|
|
960
|
+
vllm/model_executor/model_loader/default_loader.py,sha256=ie3idQ_J3DbFsrfXaT4YFHTAZuU5ATzvI2i6ifGg6UA,11320
|
|
961
|
+
vllm/model_executor/model_loader/dummy_loader.py,sha256=nyzNttnUITmIT24_a5NkzYW0cO2MGfC9by4DaVNMT1Y,1126
|
|
962
|
+
vllm/model_executor/model_loader/gguf_loader.py,sha256=o1ujuu8xCcU45CY1sBJsJFOVRANwTAJB_JOhvfhNPGs,7368
|
|
963
|
+
vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=nJWRfPE6W4oRFbiwIfMHEGqkXuea4fMdmrxWQTeAb_s,4291
|
|
964
|
+
vllm/model_executor/model_loader/sharded_state_loader.py,sha256=th2edcpO0n4OCf8rfClC_2cSPnpOPmsOrM_Rh4wHMZA,7996
|
|
965
|
+
vllm/model_executor/model_loader/tensorizer.py,sha256=8iiJ-ua5mv_G3EZpVnVqiEWPT8QJpU9lIuilwlPBC6Y,30571
|
|
966
|
+
vllm/model_executor/model_loader/tensorizer_loader.py,sha256=3m776NeJNF1B4XtB4D1Ol0zbVmAZ_0OxwIBtePIjCYU,5935
|
|
967
|
+
vllm/model_executor/model_loader/tpu.py,sha256=P5Vdz-x22ei7gwao0UKfR_4IHOZa4MJBLahrDZL27sg,4809
|
|
968
|
+
vllm/model_executor/model_loader/utils.py,sha256=wbfWVNhkFwgZeh2j2mOMHc1Av1sEKjKFsLJMMTkd3ks,11026
|
|
969
|
+
vllm/model_executor/model_loader/weight_utils.py,sha256=eBiQ5rFxMWDZI5bqkJM9a72G3OHMLDE0TkdFcLyym5U,35981
|
|
970
|
+
vllm/model_executor/models/__init__.py,sha256=rO5tFElw7pqtnqzv4kPGR-4I2x_J0MvxMYhnwWlfjTw,1038
|
|
971
|
+
vllm/model_executor/models/adapters.py,sha256=JHbuk_gA6mOmygtcLcyKjy9fi9-r4oVlrKnOEmhECvk,19802
|
|
972
|
+
vllm/model_executor/models/aimv2.py,sha256=fzq5a8XtmAmoEHnQT0kEqJRb5XX0gXR1E8bANLy3YOc,8661
|
|
973
|
+
vllm/model_executor/models/apertus.py,sha256=DWOy-mgNNT9sTPSkcq4hiBpRKu2FT6hjivkxQyMIatU,23767
|
|
974
|
+
vllm/model_executor/models/arcee.py,sha256=b2cZDx8NT_CD940BtQE_rZuIT8LMfds-yi0IRfo9178,17820
|
|
975
|
+
vllm/model_executor/models/arctic.py,sha256=Xv7DysZvLj42whvCSG67mLMcEIV-OxdYfhtPYqd4kdw,24510
|
|
976
|
+
vllm/model_executor/models/aria.py,sha256=auszCeUybZ9zeMak-dLeP_fkUQb0nX8ZYcoOEcYzZ80,25660
|
|
977
|
+
vllm/model_executor/models/aya_vision.py,sha256=kPVc1Xb-6j9WoSqGoPt9KgbHWDUXT-l2MFeBibjW-E4,18863
|
|
978
|
+
vllm/model_executor/models/baichuan.py,sha256=Rkm5B_2ktHW0BFSXaO56PdmenPb3pdsKKh2kmCeWIxA,18988
|
|
979
|
+
vllm/model_executor/models/bailing_moe.py,sha256=a4DRATtJUV_3n4cDz1Lft7MHYde41Au8YqDP7fzmDKE,20176
|
|
980
|
+
vllm/model_executor/models/bamba.py,sha256=PUFXmRfBiZ3PXox60bTf-0ANNHjsT2535jtoNyuvNh4,22923
|
|
981
|
+
vllm/model_executor/models/bart.py,sha256=ZmTR8S5HrPQS4QvVBdPWkcewXI20t8Q-dL3LG56tYkY,48830
|
|
982
|
+
vllm/model_executor/models/bert.py,sha256=yuTKyEuzpmbkjPwukYfqy0HSXRkaM-HokfEx1HU4C0U,23037
|
|
983
|
+
vllm/model_executor/models/bert_with_rope.py,sha256=YDHhXma9D1c8N_vjFt_XymXa3whQja-BDJGS53ya460,27127
|
|
984
|
+
vllm/model_executor/models/blip.py,sha256=E0Qw2SGxfBPBttkLIqhuIZTmwkS6tAy2-9R48mc3NYM,12402
|
|
985
|
+
vllm/model_executor/models/blip2.py,sha256=8bvGvZfhacmhRtXU3V95JcyNFj2fVkA6x0nvKyR442E,25913
|
|
986
|
+
vllm/model_executor/models/bloom.py,sha256=C-vgc1mlAJU__Y0_s23HdKtFKrUd1XrsuQQRk_4yPcE,14529
|
|
987
|
+
vllm/model_executor/models/chameleon.py,sha256=EQ1F6HflpxTCCuKyS96B2adwz-_mfn7huknnn9hgS-M,45651
|
|
988
|
+
vllm/model_executor/models/chatglm.py,sha256=ycU8uubPsK-331-O5qrJUT0jNZW25YfSZit34-3Dej0,18504
|
|
989
|
+
vllm/model_executor/models/clip.py,sha256=rrt1JfGp1KSVWV9ioWgIks6wZEw_WT2HKvGRuf0T0lY,14924
|
|
990
|
+
vllm/model_executor/models/cohere2_vision.py,sha256=7_IYQD_-mJ0K-0OVRWuGFFLROX8IWZpROhYUrFZoe3U,18851
|
|
991
|
+
vllm/model_executor/models/commandr.py,sha256=gxEXRDgFp__64RRth7b50jqT8POHJVVn-EJo0qaSsUo,19214
|
|
992
|
+
vllm/model_executor/models/config.py,sha256=W6P_TVToe9KEG634OEAQI2CqTyO48GeHke7OKKfHSuE,17247
|
|
993
|
+
vllm/model_executor/models/constant_size_cache.py,sha256=O7tfU9CrkKNIHVc8FIPP4IGOn_naP5Q8r-IagakUYzE,5908
|
|
994
|
+
vllm/model_executor/models/dbrx.py,sha256=eNwOH-1FVD9uLD4mP09GqE7p4wrYHI4hRQlUCxxxQxc,18447
|
|
995
|
+
vllm/model_executor/models/deepseek.py,sha256=JUylUQ30Enqzd8thLd0SS2xuf9me9_QsS2KKdLTAuUM,20075
|
|
996
|
+
vllm/model_executor/models/deepseek_eagle.py,sha256=mMjLR4Th9bNp6kt1ryqhlOb39js8KNvaqO_sNtKVxgE,9507
|
|
997
|
+
vllm/model_executor/models/deepseek_mtp.py,sha256=TvCQ45O170SvmDFU_mH5itQstrcxiDA5xXvv9e5ZLQE,11767
|
|
998
|
+
vllm/model_executor/models/deepseek_v2.py,sha256=fB5R-dMCR1ZAl28Qm9qaCDVOjOL37Gq-QnNastdDuqE,45251
|
|
999
|
+
vllm/model_executor/models/deepseek_vl2.py,sha256=SLyBCiwsnT2O_i_FwW1ymALaAflZy5b6lY3pYeexUPo,26320
|
|
1000
|
+
vllm/model_executor/models/donut.py,sha256=qovBmVU5OL26jPLQfYIPrpytfNQSxsD0CcEwh3ArWHM,14180
|
|
1001
|
+
vllm/model_executor/models/dots1.py,sha256=v9v4okMPzDUlMp9DGlEwl313g0sbD_GOYgo74ajwFTw,21993
|
|
1002
|
+
vllm/model_executor/models/ernie45.py,sha256=VhFbDQ0JTS1Qj-mHNJ1ohprdz9OYg-Jp_qxqWx7e6C8,1971
|
|
1003
|
+
vllm/model_executor/models/ernie45_moe.py,sha256=FF8jR4exZKLPSE3I0JDkIaN4h44Ez2uHCKpF9DtHEiI,24181
|
|
1004
|
+
vllm/model_executor/models/ernie45_vl.py,sha256=BXLfhOy5VsLeiS4i9dA4fcLuj-Z0ZkOcvkIE8yLR4pc,56979
|
|
1005
|
+
vllm/model_executor/models/ernie45_vl_moe.py,sha256=91jSNzWWn65Fp3g2T0lKXjELbSKfc4Ahaba0Fko20fs,29688
|
|
1006
|
+
vllm/model_executor/models/ernie_mtp.py,sha256=2lmPYBrbga51DPsWjGXG67fQVxs7JTgUH2YeZipa79A,11610
|
|
1007
|
+
vllm/model_executor/models/exaone.py,sha256=huoLj05GY3AufCF2YSTMRpTl7m7GvFx_k1z2_nIJsDE,21185
|
|
1008
|
+
vllm/model_executor/models/exaone4.py,sha256=2coKkz9e7Lflmm2LZYp54BAyAiY1XreocKLnCGO9hJE,20764
|
|
1009
|
+
vllm/model_executor/models/fairseq2_llama.py,sha256=62IX9r3OrOKXD-TiNJRx_mI_TMLyqUOvmQxk8aoUZ-g,6555
|
|
1010
|
+
vllm/model_executor/models/falcon.py,sha256=W6lLM8zKx1Yws8XvQqdlhZ--rV6KeQVyoD4hyT64zuw,21421
|
|
1011
|
+
vllm/model_executor/models/falcon_h1.py,sha256=Vz0-Lr57MsiGN7Pfd1HC6jZV7S6v2Ztr56Vow3yQgZg,28578
|
|
1012
|
+
vllm/model_executor/models/florence2.py,sha256=dHCnByy8ocsnuxCC_UISlid8ELgDyzV6sESKooPrPS8,39445
|
|
1013
|
+
vllm/model_executor/models/fuyu.py,sha256=b3J8pNdIbC-cnWSxzCdHXrR5WFxZOViid19gIsh3wW0,14907
|
|
1014
|
+
vllm/model_executor/models/gemma.py,sha256=1dJszKvRWg6bvhFHlA0hz663k4sqzGWrpZpQaSkxrgs,16422
|
|
1015
|
+
vllm/model_executor/models/gemma2.py,sha256=tdaa6-OiHuPHHwEr6KL83BsGFwxrfj9GUzZo8gGxYOE,17380
|
|
1016
|
+
vllm/model_executor/models/gemma3.py,sha256=a3tKbczrwkcYPWqBjCUP94bE_uMXk1cqbU2FH70VzHE,22031
|
|
1017
|
+
vllm/model_executor/models/gemma3_mm.py,sha256=9Ct9rQWnUwqVgdZoMKJBcCEORoBDBaL4BiGZyvJUAnc,26396
|
|
1018
|
+
vllm/model_executor/models/gemma3n.py,sha256=jEhuhsUsv7XS2i8BNdKvkdNo2pGdGcIcDhxWABaaBHM,33069
|
|
1019
|
+
vllm/model_executor/models/gemma3n_mm.py,sha256=YcN7CVHR-HYaMe1lF1_NpTqyM4044qOgCsKIAnoZ134,31066
|
|
1020
|
+
vllm/model_executor/models/glm.py,sha256=d2mDle-FA4NVjt8bVZwYQm1ddtp75b8Ji-1aVlYKb28,1059
|
|
1021
|
+
vllm/model_executor/models/glm4.py,sha256=J_NOzM6avf9dNJjJkA6XnKaXblh-xEaynmLvPrcShNg,11864
|
|
1022
|
+
vllm/model_executor/models/glm4_1v.py,sha256=11yAOneOZ3tcy4By7ls-D76R3jOP9ENlmofkCL-zrLY,64380
|
|
1023
|
+
vllm/model_executor/models/glm4_moe.py,sha256=3omZ8KlIBHASK8erxJ6TtdbX7Cw2kXoZVdOlH1H9JAg,29224
|
|
1024
|
+
vllm/model_executor/models/glm4_moe_mtp.py,sha256=MylqUDlN3kBLgaZQTLEB0CWvD6UPIbmAlwpP1Zz2ibs,12934
|
|
1025
|
+
vllm/model_executor/models/glm4v.py,sha256=254goB4J7VRk8He4i26vUAj8BPmjAegbjjsA2fyCqdY,22574
|
|
1026
|
+
vllm/model_executor/models/gpt2.py,sha256=aQTMr8decmVnhnBbv9-OUKgEcaIlRuAC9_oUgJhJM2A,14911
|
|
1027
|
+
vllm/model_executor/models/gpt_bigcode.py,sha256=cWvRd0ekwMwIRR4BJasKsK0LQtZjYIVCVgoyvIiYdvI,13586
|
|
1028
|
+
vllm/model_executor/models/gpt_j.py,sha256=NRgReVkb2ONm-30LmmmI8zYf_B5NAGDkprY3CTxWNdA,13287
|
|
1029
|
+
vllm/model_executor/models/gpt_neox.py,sha256=LX-HP9m2_gjlfnxUh1_2UbbfeRVzb7-3xatdY3uml68,13425
|
|
1030
|
+
vllm/model_executor/models/gpt_oss.py,sha256=WghlOTtYmygRX_-BhN71uZkLRoDiE8xkLDHUW7QTt64,27865
|
|
1031
|
+
vllm/model_executor/models/granite.py,sha256=RIfYEOWIG98AZkl3pOB5Vh8NewimzkF74g-mFPHCClY,20394
|
|
1032
|
+
vllm/model_executor/models/granite_speech.py,sha256=iJ6y42H7KQSB36h6pSs4QmKA_F1kAYQU6d_PRLxbgl4,32116
|
|
1033
|
+
vllm/model_executor/models/granitemoe.py,sha256=ayVHJw0qeTShUY0EKRhh8HJdI6_3SRerEeqEwS4flew,22809
|
|
1034
|
+
vllm/model_executor/models/granitemoehybrid.py,sha256=gBVUCqwRNqPUc5OLyjkFKgnKid385RV3Mnb10gTc19U,28633
|
|
1035
|
+
vllm/model_executor/models/granitemoeshared.py,sha256=n0PGvm_yHasED4Eu9ylcszG018zCWwNaIFFe4VOaeGQ,13866
|
|
1036
|
+
vllm/model_executor/models/gritlm.py,sha256=9t42Jgz-CyDVeKRXMI6M5WpYEwBef4_og1X-2gtcnkE,9540
|
|
1037
|
+
vllm/model_executor/models/grok1.py,sha256=A-OBMgNKINKX9RchTYxuys5sglO8rDUCaT8sEnnvdsk,22745
|
|
1038
|
+
vllm/model_executor/models/h2ovl.py,sha256=qmQDkgik90iCazP7eu9oYVsg2y5VZLBCur6Mxppw9Y4,18090
|
|
1039
|
+
vllm/model_executor/models/hunyuan_v1.py,sha256=oBIQKKEjxF7Xgz-Itqd1x5IGYGwE0Ist-HvZb7ibeUE,36899
|
|
1040
|
+
vllm/model_executor/models/hyperclovax_vision.py,sha256=r30rhhl9ttINOrLf8JZEXtCYytKzgtlMjQOSQ8f63mk,44834
|
|
1041
|
+
vllm/model_executor/models/idefics2_vision_model.py,sha256=eUSZApLShwOSuo9AeTtpCdm7LAxSuJkYUfnGkL5tz0Q,16039
|
|
1042
|
+
vllm/model_executor/models/idefics3.py,sha256=MdZr11_FJ7SiRaKVAD0IyI3LRw-WWrJoczMlyqVDe44,27690
|
|
1043
|
+
vllm/model_executor/models/interfaces.py,sha256=mo_f7qeJzyNCP73MLCTIoeJGIhuMTstlHxl0lF229Sc,25992
|
|
1044
|
+
vllm/model_executor/models/interfaces_base.py,sha256=3HxaWfA_wSqb4tallGp3PFLKNRHO8iK3pj76aBWPvII,5245
|
|
1045
|
+
vllm/model_executor/models/intern_vit.py,sha256=qZ1oPaRKBsEe82BVz9q0jW8kwygc2ym3CHOGmHlZdyc,17405
|
|
1046
|
+
vllm/model_executor/models/internlm2.py,sha256=O-g4n_IlieVaP1hmqqh0Jk9ruXesDOuqtv-jKV-O4nM,17407
|
|
1047
|
+
vllm/model_executor/models/internlm2_ve.py,sha256=h-6wadMrKNRxOuJJH_fF2A7wVnU10O2tEsFkTQEhtzM,5839
|
|
1048
|
+
vllm/model_executor/models/interns1.py,sha256=yp2mIpxOS6FOhzNVkOFaQ3n9aD6F1NgjjNIDqS_HqNI,33169
|
|
1049
|
+
vllm/model_executor/models/interns1_vit.py,sha256=HjZxqPHlJZC6u5LmwIZ7LZkdMipgvis_x6MCpqYrNAg,15819
|
|
1050
|
+
vllm/model_executor/models/internvl.py,sha256=wG9OLg0cPZLnNYh-zLNi7TQIYFB-BFN2iZYA-YB78EU,52208
|
|
1051
|
+
vllm/model_executor/models/jais.py,sha256=p_CX7XzZR0yr78ad1RZktTGHCY8WOdu2vGxfgAVhEgU,14653
|
|
1052
|
+
vllm/model_executor/models/jamba.py,sha256=vU8FjsVFub9YTY2JU4-GbTcqdMq38A8zHzf9CrdDib0,25826
|
|
1053
|
+
vllm/model_executor/models/jina_vl.py,sha256=eUmhiNQQS6bbc8nApR11xUPIliTuoig7tLuLUqFtXJU,5610
|
|
1054
|
+
vllm/model_executor/models/keye.py,sha256=TiJJm5j2X2lUvjILLrNZJ9c6-TSH4983Vpuuk36h5E0,61659
|
|
1055
|
+
vllm/model_executor/models/keye_vl1_5.py,sha256=xmDV69ufldBH-KrSQGjOhc3YQ_s0Dg1LrfEHO4S_ELA,23156
|
|
1056
|
+
vllm/model_executor/models/kimi_vl.py,sha256=nRhEZd67rouWtIVDAbCxNtuI_qRU0U2esEogQW2IKRE,26477
|
|
1057
|
+
vllm/model_executor/models/lfm2.py,sha256=9RRp7Y11TkxxNrcC_znGkSiIchiouSX5wfZVk6Iipt0,20920
|
|
1058
|
+
vllm/model_executor/models/llama.py,sha256=sxPiiOhS2Y2WzAHwiY_0mvcsdXh6EH-jSE7Qf8CRTfI,27437
|
|
1059
|
+
vllm/model_executor/models/llama4.py,sha256=SyEdd04ufDPG9oXPrUJztSdaBh4Qgi5vtMfS_SvLsjw,31735
|
|
1060
|
+
vllm/model_executor/models/llama4_eagle.py,sha256=YiKaZPwQ00y7MegcKi-aBr9EhQ5dTqtexmuythDEIGQ,9611
|
|
1061
|
+
vllm/model_executor/models/llama_eagle.py,sha256=Gwzqrc4YRGuMtKrFCty8NzEVyUPTEwJBFQ2zv1uA4Qs,6143
|
|
1062
|
+
vllm/model_executor/models/llama_eagle3.py,sha256=q_w3B5egzW9NQqPNSbO4CKWjLsSaarkmnwaPOea-Se0,10616
|
|
1063
|
+
vllm/model_executor/models/llava.py,sha256=cgKtgsvFUtxifsIjutthW-vav0ppxNeOFCYzaEv4Nw4,32520
|
|
1064
|
+
vllm/model_executor/models/llava_next.py,sha256=c_cxfehXmsKNYVOJt5oGfBpTKWWmHk4LWIj5Gf24L-g,23680
|
|
1065
|
+
vllm/model_executor/models/llava_next_video.py,sha256=Eqwvg49RqrbIcWF3gPysUgq3ahwrJqHN5Vm6-SO8spY,18247
|
|
1066
|
+
vllm/model_executor/models/llava_onevision.py,sha256=hPsZd3LeEsQp49poev2Llavl1AVYcHgN7AAKUlqPRC4,36746
|
|
1067
|
+
vllm/model_executor/models/mamba.py,sha256=upzWM1fK3Tq_XKehKGZGF1hwNfkU9r0kqD3sZ649rZY,13176
|
|
1068
|
+
vllm/model_executor/models/mamba2.py,sha256=ccpC2KeQ7Mt4woJw1pCCvBw1O4u5y38AU52YioETpAQ,14404
|
|
1069
|
+
vllm/model_executor/models/mamba_cache.py,sha256=D2rSdDGAWaouECqoeOlocZT17pMNWGJgtDEVQ4YO5T4,3338
|
|
1070
|
+
vllm/model_executor/models/medusa.py,sha256=iR59lwoGI-KtA_rh0O7ABUJiDOWocdbdrAbND6qmqVY,9003
|
|
1071
|
+
vllm/model_executor/models/midashenglm.py,sha256=Nbkm5gOX9Zp6C5jRg3kCukF4jkyK-oBXybx9-ufZ_i0,28813
|
|
1072
|
+
vllm/model_executor/models/mimo.py,sha256=E5Aw6laCV_CVcp8Vj0eFFYuACgKWyPJ36Gd4BEi6nqc,7858
|
|
1073
|
+
vllm/model_executor/models/mimo_mtp.py,sha256=sLpK9o2RzaZ4N3V1Zw9dooE94xLy986KokOSTh-ZdXE,11051
|
|
1074
|
+
vllm/model_executor/models/minicpm.py,sha256=13KBomNMz2ETOtUU3TkJJAmMYJ8UWuGV1PvCP7CMZzE,23943
|
|
1075
|
+
vllm/model_executor/models/minicpm3.py,sha256=3gR9YhnAHhgoi9hfQupHmNhhAt--aeyMDMerp7sncuw,9429
|
|
1076
|
+
vllm/model_executor/models/minicpm_eagle.py,sha256=qOHJH4raDUbtTJYiOWpAUBfYo3dUow4ImkdZfx6K88w,15901
|
|
1077
|
+
vllm/model_executor/models/minicpmo.py,sha256=1Scx7f0SRT7k9QjgdbGWasbcMGGGE2pwtEORPzBMIWw,30706
|
|
1078
|
+
vllm/model_executor/models/minicpmv.py,sha256=g1AZf3_nEgvHd28gyEoYoJXFj1kVvkSvWaQC0ezlJvQ,66257
|
|
1079
|
+
vllm/model_executor/models/minimax_cache.py,sha256=k52vWrBlTlPPEOxeZ4Pn8scFroolWzI5DYXpBtX1fjo,1212
|
|
1080
|
+
vllm/model_executor/models/minimax_text_01.py,sha256=ihz2wOBR23mIXAFvbcTkpAowwnjnKwdT_9dDc8btqF8,41186
|
|
1081
|
+
vllm/model_executor/models/minimax_vl_01.py,sha256=FmAWQFLDEIKxzjtZre91TMTYe7Lu7jZE0mHc7-2LAD8,17435
|
|
1082
|
+
vllm/model_executor/models/mistral3.py,sha256=uZz-28AHDKSQQu82xCyz01WSD6gHe1dy7vgbW8vtFfk,24018
|
|
1083
|
+
vllm/model_executor/models/mixtral.py,sha256=LeDPyAADVHx3IGEJazkmcquqxL9TnPWzqtqLQuUYnzI,20472
|
|
1084
|
+
vllm/model_executor/models/mllama.py,sha256=cp58DcQXLg5mub9iB8zn8KM1PomQTt5vV88-6Z3iO4c,69765
|
|
1085
|
+
vllm/model_executor/models/mllama4.py,sha256=eu93MxTmiOdrDHw8ePgMp-QpeUg-uNfy8hs8GwNRwdo,41102
|
|
1086
|
+
vllm/model_executor/models/mlp_speculator.py,sha256=Y7j6_gQPcxM53DHel_hLHdT2Xm1t3V6bv2_Q2e_jgFI,7965
|
|
1087
|
+
vllm/model_executor/models/modernbert.py,sha256=kH1_7XJWtBP5CgcSKKEdln44dR-zd4NTDtAYl8MCxPE,14114
|
|
1088
|
+
vllm/model_executor/models/module_mapping.py,sha256=vNEOOezDnDR5JgMltbviAANLu8CM6tQdr3RX6tZu_i0,1844
|
|
1089
|
+
vllm/model_executor/models/molmo.py,sha256=t1yy7BXThaDBGRn19pVYJafFsPNIEgFscVL5j8KVV_s,55011
|
|
1090
|
+
vllm/model_executor/models/moonvit.py,sha256=vKlTKjKv84oJbQNxdwyOCn-fGPKje5DAopGPFC92TC4,25638
|
|
1091
|
+
vllm/model_executor/models/motif.py,sha256=7Fj0iyl7H23Wa6hOvwWjvnwLiri8NLKTMP2vOvsAAYs,13929
|
|
1092
|
+
vllm/model_executor/models/mpt.py,sha256=nzDPLDcwUL5o4RkSxxCNLm76aASdLdi8TeIT_cDd3GQ,12751
|
|
1093
|
+
vllm/model_executor/models/nano_nemotron_vl.py,sha256=Xf-7m5cfM1B6LnkOUWocwT8JF-scwBsyDRbeAFJ56u8,52540
|
|
1094
|
+
vllm/model_executor/models/nemotron.py,sha256=JPqKoX86HCz49ThVzRTl3kP2kt55kw5Lmt-nK3ote4k,20753
|
|
1095
|
+
vllm/model_executor/models/nemotron_h.py,sha256=t2JSMyK_uFrhkwG_ekVcbDMuEJI5KAh_d6na9wauiNY,23367
|
|
1096
|
+
vllm/model_executor/models/nemotron_nas.py,sha256=azsspBlccJF1zO3H8ztV9VRgkOXHwk_0P062TITN0Yk,19219
|
|
1097
|
+
vllm/model_executor/models/nemotron_vl.py,sha256=L9w0QYwK7Nmj1zhUlM7TJeGd07FyQL7OxViHcXE04Sg,24158
|
|
1098
|
+
vllm/model_executor/models/nvlm_d.py,sha256=13ydfbCEUpu9XkGdO_sbj1zpaH5H3hKgv5-PGJTHujQ,7622
|
|
1099
|
+
vllm/model_executor/models/olmo.py,sha256=VFrQtao9pn5YeFT_QSPLwYIw4zc-MFLQIbpjo5H7IPc,15428
|
|
1100
|
+
vllm/model_executor/models/olmo2.py,sha256=1V1_aF2eTfOnrDwvF0o8VcPY_6SodlqclkzGbtQ525Y,16356
|
|
1101
|
+
vllm/model_executor/models/olmoe.py,sha256=XUHIVUI35AUA5KZc1Bxo7P8vXsb8Si6p3OxLKaQkxEU,19892
|
|
1102
|
+
vllm/model_executor/models/opt.py,sha256=pDxxyvdEE3vfo1WGd8bWiUfBQWlDkl8wds-_D1Wun2I,16610
|
|
1103
|
+
vllm/model_executor/models/orion.py,sha256=KW1SoNjZBaAXAfTc5SSuwzT4AIJo95ubYXx-TZkBFZ0,13900
|
|
1104
|
+
vllm/model_executor/models/ovis.py,sha256=mpteDS2oiVuSF9UaDlJk5VEw4yvhFQVXwvpywrE9JrE,22411
|
|
1105
|
+
vllm/model_executor/models/ovis2_5.py,sha256=REhPCrnCJvSVs-yinvtJGPNrRV0qJxWL37U6C0OwJCU,24965
|
|
1106
|
+
vllm/model_executor/models/paligemma.py,sha256=lDW4VWF6yT_LWp8mfCMMw-0xKpDiNqHWToJMeGN8nsk,15396
|
|
1107
|
+
vllm/model_executor/models/persimmon.py,sha256=RWaD4CluCjZP7EoujuFgalXaBp9DRAA5F0GwKCRhRVs,14366
|
|
1108
|
+
vllm/model_executor/models/phi.py,sha256=QSnkgUHTvnuI_ughWXnUqV5esCbm3TIRGznz29fUl98,14210
|
|
1109
|
+
vllm/model_executor/models/phi3.py,sha256=OdDcrMZ2IYHzg_R_gu89ae3lijNSFlxUXKTw4mmcR8U,457
|
|
1110
|
+
vllm/model_executor/models/phi3v.py,sha256=FoNH0k3yb_LzavhROn2bYlfF1YiPzpi12syqnjX0kEs,27697
|
|
1111
|
+
vllm/model_executor/models/phi4_multimodal.py,sha256=LPVB4jLAXPlTK16I8LBitvPD8CwyB6Nu-8Sewts2o6I,57928
|
|
1112
|
+
vllm/model_executor/models/phi4flash.py,sha256=Kh37-FP6kx8bHap_EhejXnDGpxtXOuk5ZyfdgBkw84Y,30083
|
|
1113
|
+
vllm/model_executor/models/phi4mm.py,sha256=efey5elf14oXI6G8YxAJzQNWKBkRPEvm7tAZHOByBfk,50267
|
|
1114
|
+
vllm/model_executor/models/phi4mm_audio.py,sha256=OtLomyHZ1aR_0GP9H5e49-u1HX3PiA81TcQelWaoW_w,51162
|
|
1115
|
+
vllm/model_executor/models/phi4mm_utils.py,sha256=8RE6JOwyxFfL89OEykkbSlLalOFk_2zsHASi6VOtP8w,67478
|
|
1116
|
+
vllm/model_executor/models/phimoe.py,sha256=mGt-6aUFzA1ZApBr2-4yYIpOwdqgwnkHq5c-tHpnB6M,25376
|
|
1117
|
+
vllm/model_executor/models/pixtral.py,sha256=6oSOn8FoWCoM0_7X2G83olD_d4ewkxf-CcdKbbfPOFg,49709
|
|
1118
|
+
vllm/model_executor/models/plamo2.py,sha256=UC__-55h6JBuLCZ2CAVFRf4ztNoLGf-vj8NJ2WEJ6YM,46406
|
|
1119
|
+
vllm/model_executor/models/qwen.py,sha256=CkNqnt_IUfjf5cRSBuS6tYLTfB8KVwMts6IhTyhS9gM,13954
|
|
1120
|
+
vllm/model_executor/models/qwen2.py,sha256=WDIT_adVpSFIf_q3z7IoV0Ww8AMfvraKcgtHVd9ibOI,21080
|
|
1121
|
+
vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=O-D-OB_m988JQgjdLdp4qI05BCqsG_WofbegJiBuk7E,40536
|
|
1122
|
+
vllm/model_executor/models/qwen2_5_vl.py,sha256=hreKhuOoZ6axFik6Do4Nk1Vmdxibh6X-magWFn1Jd-M,50264
|
|
1123
|
+
vllm/model_executor/models/qwen2_audio.py,sha256=Hs36h0RvF0GnGsUSaI6lq2qfLUpg72WhS-UzOeRyR0Y,19442
|
|
1124
|
+
vllm/model_executor/models/qwen2_moe.py,sha256=1PaRauKOyZ40rcFjHRxI9zfkChDKa0phSlu7zMmf4mw,23579
|
|
1125
|
+
vllm/model_executor/models/qwen2_rm.py,sha256=lD5LAuxhTKxac4RuRqzbFZBtwb5RYn1ahXPB2IY_oQ8,4438
|
|
1126
|
+
vllm/model_executor/models/qwen2_vl.py,sha256=ujniszGFCruhBlyw-1jfdOongGaF_oG7_emJis3t_k4,57395
|
|
1127
|
+
vllm/model_executor/models/qwen3.py,sha256=R6utoGoiWPa9SO1uUPCKymcVPYqmsoYtr0ezaO4RD_k,13310
|
|
1128
|
+
vllm/model_executor/models/qwen3_moe.py,sha256=wRg6_ViUzZ32ULsTpjGV1s39FwIGqdz4sx-h3fO51bg,30694
|
|
1129
|
+
vllm/model_executor/models/qwen3_next.py,sha256=DVbLQXbVoS9Xto2AURJ5BMEj1Y61ibHijho_WyhvpR4,52259
|
|
1130
|
+
vllm/model_executor/models/qwen3_next_mtp.py,sha256=UADlGFe92XUvx8bkoN6QSfG9p5G5fvZJflgCmcwB-Z4,11884
|
|
1131
|
+
vllm/model_executor/models/qwen_vl.py,sha256=AJ7YwxuqV3XvW1b2MdU-SCXc8WLITYmscqIu6lxH4ZI,27261
|
|
1132
|
+
vllm/model_executor/models/registry.py,sha256=0bXS4ky0oYjctL2QMiRcMEaW0C-H7KmtqvYYdoEht0Q,39633
|
|
1133
|
+
vllm/model_executor/models/roberta.py,sha256=_NmoejqZikPqCWKJ8T3e62WQN1eRhI-dWXEcHFjgV5g,10559
|
|
1134
|
+
vllm/model_executor/models/rvl.py,sha256=lHKPSwg6Oby1fR19Eci9kAYxNoKlTl5yv1-XLCsCNdc,3411
|
|
1135
|
+
vllm/model_executor/models/seed_oss.py,sha256=CNGTE-osh8WByfFD4uOmvf9riJmttk5tJqHAyZLcD_Y,18982
|
|
1136
|
+
vllm/model_executor/models/siglip.py,sha256=zfwSZK8jlQL8B6_C1WvF_sUlacyRNMIDXk_Gp2NPrfM,18720
|
|
1137
|
+
vllm/model_executor/models/siglip2navit.py,sha256=LU6ZiB0lT21GExnUjRxdDKckcXemJxAkHYSegkawGu0,27571
|
|
1138
|
+
vllm/model_executor/models/skyworkr1v.py,sha256=q1sZp7kMbwx1rWR1xSVn93HL7R23PCZYRdUaGMnvIeQ,32939
|
|
1139
|
+
vllm/model_executor/models/smolvlm.py,sha256=UHJHGKiMjLelyQBxxetY_MjFsB5neGCTXE3FgGkSIlE,1614
|
|
1140
|
+
vllm/model_executor/models/solar.py,sha256=HLDduE5re-mJnZEEq6djQTugObzWM6HBYFMs3yhJaXU,19962
|
|
1141
|
+
vllm/model_executor/models/stablelm.py,sha256=1qDunddBgfCo-9cF9S67NPJ3SJlvkxyuv_TwNMmIRsk,15045
|
|
1142
|
+
vllm/model_executor/models/starcoder2.py,sha256=RvK_dHUuwJlpS3x4MJrhdmeobBskA-a7m2OmNUpnAK0,14648
|
|
1143
|
+
vllm/model_executor/models/step3_text.py,sha256=Hzzutgvg4aY-qtkjJTBAAlS-pxmlml5pKN28p8V1Bho,21654
|
|
1144
|
+
vllm/model_executor/models/step3_vl.py,sha256=q7MNQzWFpvE2b6hWAWavm7MgehFM0QzChnGUgD-bD0A,42683
|
|
1145
|
+
vllm/model_executor/models/swin.py,sha256=u0ocae8ZHEbpPMPxgIdJGhwiuy-COZBqCcSguEDYz_M,18103
|
|
1146
|
+
vllm/model_executor/models/tarsier.py,sha256=LT1Q-nK3PmZyhzsWRb0sHu4rV5eyIxjUiGJtWv_1nDA,26275
|
|
1147
|
+
vllm/model_executor/models/telechat2.py,sha256=aLab_2TYAW_ogYlYpFuTyZ7eqIsA5zvrOWXzNuC-Rhk,6395
|
|
1148
|
+
vllm/model_executor/models/teleflm.py,sha256=8BsSo5Ox4ENo4Y1UKicd2nq41lksPZhW-ippU-498NU,3212
|
|
1149
|
+
vllm/model_executor/models/terratorch.py,sha256=eIZtd9OjwjebxqH_fl3ACQW_n8FEdiZ4tz78QCh6dOc,11103
|
|
1150
|
+
vllm/model_executor/models/transformers.py,sha256=nCOAIiOEWZ2gWauxY2O9-T8dg4dov1-8ZQy65rJOT3k,35676
|
|
1151
|
+
vllm/model_executor/models/ultravox.py,sha256=bB0wTnCt8_8cZYnSyGeXf1nDcif8HNCLO0A5e7Of2iY,27372
|
|
1152
|
+
vllm/model_executor/models/utils.py,sha256=ZsA4uomXcwM9WxGPloPB0_TSoCxuh6dtr-Q7goKEFss,26524
|
|
1153
|
+
vllm/model_executor/models/vision.py,sha256=67T_7ObuubMOZyqhcysCpRhvkxEQ3YlaX6BVwIrg1To,4365
|
|
1154
|
+
vllm/model_executor/models/voxtral.py,sha256=FKyMRLfJWKuVnEKipkoMRhpP4fpGMeiL3LOhLe41-4Q,31988
|
|
1155
|
+
vllm/model_executor/models/whisper.py,sha256=ahhZEC6UcyP_Pd2j-PnlNY_ZYTaXr1t7gI3fVDofCIc,34965
|
|
1156
|
+
vllm/model_executor/models/zamba2.py,sha256=wskW4mZmALE2qeKXvXnN9AnJqhEliFtwfez9JLhO51M,41906
|
|
1157
|
+
vllm/model_executor/warmup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1158
|
+
vllm/model_executor/warmup/deep_gemm_warmup.py,sha256=Q5_cpL_EVnQKaBaKN75nPOro9LePpTGr8ZfWKPhdx2Q,8351
|
|
1159
|
+
vllm/model_executor/warmup/kernel_warmup.py,sha256=04wt1em-YPIoSfTD5FV0b6Wgn2afmVv3XppMTDXly1E,3257
|
|
1160
|
+
vllm/multimodal/__init__.py,sha256=osxKLlyFo8fJfYFEmRSCdOAqil3ZM-HnUOhWmD--Ug4,1132
|
|
1161
|
+
vllm/multimodal/audio.py,sha256=YNvIWS7DJHSbV1RJSo0xCpoP4vOFzbw_Ot5U3FEGHvw,3478
|
|
1162
|
+
vllm/multimodal/base.py,sha256=fL0_3I3ChMjAcExvTQc3YRt4iuo-Qd9v9ys7eoK-w-4,7000
|
|
1163
|
+
vllm/multimodal/cache.py,sha256=-s_2ZxKdaTcPRDL39rF587rEXGuSDWMBU1THLZdYsI8,15314
|
|
1164
|
+
vllm/multimodal/hasher.py,sha256=VS66fhFLaCpwP26s1TeL3cN_zSau_DaZhoZjEE7BnWI,3713
|
|
1165
|
+
vllm/multimodal/image.py,sha256=aLJbqxgnsdtv-DZpE8rXsK-bK5FlIsofw6Duag1K-1Q,4428
|
|
1166
|
+
vllm/multimodal/inputs.py,sha256=GxbHtzRUmXD5rtS8cTokmxSA9e-3CwTqExxg8BwqqoU,31195
|
|
1167
|
+
vllm/multimodal/parse.py,sha256=vTK7xECzF5vgdMfCeykQMgOhMztYBsQ7n5ju0F9kpC0,15777
|
|
1168
|
+
vllm/multimodal/processing.py,sha256=arziBn4r_XG_xljLG-LkY1hv6rfjm1pfEKMHL4JbcQ4,64790
|
|
1169
|
+
vllm/multimodal/profiling.py,sha256=Ls5olvUoAaRGdwPaarMKzcbauBY4UefUNWpBfJ04AAM,11117
|
|
1170
|
+
vllm/multimodal/registry.py,sha256=0ODdiqQkLm-6bl1eVvp6UcysgDdJzoo05bLGX8Zisz0,12917
|
|
1171
|
+
vllm/multimodal/utils.py,sha256=HEm2FM-IS0IRisEfN9Yphblpqe7tq7RBZu-fwv_rHTY,26908
|
|
1172
|
+
vllm/multimodal/video.py,sha256=XOzSaHC1zvas0Wbh5-h2v0_94xX3Cl7arb96AKv7xYo,10197
|
|
1173
|
+
vllm/platforms/__init__.py,sha256=SL8lJmGPX0NTlN_UulLPIe5xrP0dDrS_Rbo8eEcn3Mc,9715
|
|
1174
|
+
vllm/platforms/cpu.py,sha256=9hD309im0rsgbKqhtX54KDwwcCrHbXWy6uTRxz1IPug,13318
|
|
1175
|
+
vllm/platforms/cuda.py,sha256=OekqFB54aAxS-iUL__JgHguqPx9rpo9pJLQpPL5dDWc,30341
|
|
1176
|
+
vllm/platforms/interface.py,sha256=iRfVdRBIBCWRlvq6WLaSOCa8JjeRscjVOVr-XbTPC0c,19469
|
|
1177
|
+
vllm/platforms/rocm.py,sha256=o2TMqv75mP-3_rprTw-fEyphCx4f0q9aHleTPTV5vSo,19720
|
|
1178
|
+
vllm/platforms/tpu.py,sha256=IzaAzgxCaC6JyL1MSh2pI9gcCno7ogFtDoYHYjH_UjA,8545
|
|
1179
|
+
vllm/platforms/xpu.py,sha256=UAW8WtnEPMiaM8V4hy0hEE_Hu8GGGSg5jVYnYS6jYNY,9566
|
|
1180
|
+
vllm/plugins/__init__.py,sha256=ZRORMWMdEHWT5MyQCUprDf6kjLx3RpSi8nZ9MAlfx5s,2342
|
|
1181
|
+
vllm/plugins/io_processors/__init__.py,sha256=rDFMjhLEr6n5OBkgUvUivLzkQH-VoCOWP9ZnfdcgZSE,2547
|
|
1182
|
+
vllm/plugins/io_processors/interface.py,sha256=wyjPw_-JOW-2WIOxdqVFMIwrpakeWmag0ckSXGfBr1g,2367
|
|
1183
|
+
vllm/plugins/lora_resolvers/README.md,sha256=-QNm2DW1CJ8jXT_DReEycm4e9qCk_fI-HJMzM_CgPU8,830
|
|
1184
|
+
vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1185
|
+
vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Ic4o6SWF7DeDhNAAE1dxzaAMb_0L03DNzM0590FC1Fk,2086
|
|
1186
|
+
vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1187
|
+
vllm/profiler/layerwise_profile.py,sha256=ePkIStAYP58wRo3WUuy9dvOMvd4t5fRPeUN2QDALW0U,13887
|
|
1188
|
+
vllm/profiler/utils.py,sha256=zh9V6T6baIqC_EXfG39TUF2-d0z20JVqxfVtKWFDl6Q,4714
|
|
1189
|
+
vllm/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1190
|
+
vllm/ray/lazy_utils.py,sha256=WrCc1ujOpiNakx6xqEXTgIPxsWyqcXAqHXZPa-3QXEI,535
|
|
1191
|
+
vllm/ray/ray_env.py,sha256=qQGwVH2dWUZsL8wLJ1Y5RRH--nAm_RywVJHM-kRhZHs,2627
|
|
1192
|
+
vllm/reasoning/__init__.py,sha256=Fz1_qEQsPj7_AbAeHA3tf3-WM0eajfF2T5ABQwUAyvU,998
|
|
1193
|
+
vllm/reasoning/abs_reasoning_parsers.py,sha256=uuJYowxR9rfRXunQyO2PdSt1Q5hfJ8TbYRHS15MQWlE,6909
|
|
1194
|
+
vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=fVAV4ZsMfd_6bB3Rf6ucSGnMJLnI1NjcAMA2i2yucwA,7465
|
|
1195
|
+
vllm/reasoning/glm4_moe_reasoning_parser.py,sha256=uxHeK9Ax0dLRXRUH9JG_rFNQklZWwWzCulOcvtSORAA,6524
|
|
1196
|
+
vllm/reasoning/gptoss_reasoning_parser.py,sha256=Ydr1RIeAkaJI2D-vtKZT88JEscVyH_NB9D42l3dfdZA,3438
|
|
1197
|
+
vllm/reasoning/granite_reasoning_parser.py,sha256=1D8ojEdvWm391P8xoovSgLsEk2pESZIeNv3vqwfo-Yo,15899
|
|
1198
|
+
vllm/reasoning/hunyuan_a13b_reasoning_parser.py,sha256=u5X3LYonDam0XXL_yrp5w9fPWKA5XQnJXSRK4ARKGsk,10160
|
|
1199
|
+
vllm/reasoning/mistral_reasoning_parser.py,sha256=Rn-0SM5VTRHBoAHJGrFmFnAOvvlHQ10GTzqr4FkYktA,1778
|
|
1200
|
+
vllm/reasoning/qwen3_reasoning_parser.py,sha256=gzC5_aje9dv5Juw5TRXQIOOP4QRPa_BXZkcE6cmrb68,6496
|
|
1201
|
+
vllm/reasoning/step3_reasoning_parser.py,sha256=glSWMte01rI8BDo-VjvRKstckT-jhoais0lG-49u4G4,4249
|
|
1202
|
+
vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1203
|
+
vllm/third_party/pynvml.py,sha256=HRQEbE5ZB-AgMIySG4j24hjlEgSGLrNvHJUq7UawCfA,234653
|
|
1204
|
+
vllm/transformers_utils/__init__.py,sha256=yVNs7WNM1UWvqmKYPW-R4D9NXhYWEjKYQKlfcpxL5HI,910
|
|
1205
|
+
vllm/transformers_utils/config.py,sha256=ZWMSgzwApHlLGo0xMvViJaWJbKhztg3Zb9zqrnm4x1k,38473
|
|
1206
|
+
vllm/transformers_utils/config_parser_base.py,sha256=mHcEv_VAIJwK7oihh19ppZsX54cwoZNd95WLSJBmLu4,586
|
|
1207
|
+
vllm/transformers_utils/detokenizer.py,sha256=z9t00r9oVLqphLPcBTi0StA4x_avrE2jwMOtQKEB6S4,7324
|
|
1208
|
+
vllm/transformers_utils/detokenizer_utils.py,sha256=uWAkqoehhgiYFEo-eOl-6Jk_Fj0B7kZRj35q7fDi5PY,7645
|
|
1209
|
+
vllm/transformers_utils/dynamic_module.py,sha256=JZ6XzmMjjijJhA9WZVLOnjKxprRFYOb091yaTPm8O50,1854
|
|
1210
|
+
vllm/transformers_utils/processor.py,sha256=2X-_WxusIdEpqgJelEHCfIAzq_dETtgq2IJDrCw0N-w,8366
|
|
1211
|
+
vllm/transformers_utils/runai_utils.py,sha256=uJHksHndOj08UaglGxWu7OVFH28SGGE_uHqrRd3GfRU,3045
|
|
1212
|
+
vllm/transformers_utils/s3_utils.py,sha256=Ey6ySLDeNDq0Lud8w0-Qe0p1zJS4v8YjznwLDB_DTX0,2749
|
|
1213
|
+
vllm/transformers_utils/tokenizer.py,sha256=qAYzrDqPG1ZbN9w8ZQw--hipEAzXmP_pIHV6lHyo31M,10423
|
|
1214
|
+
vllm/transformers_utils/tokenizer_base.py,sha256=_1iqKJZTSQW9ITGpZkC-A1lhYw7ND1ZDzpY3SpDhj_c,4029
|
|
1215
|
+
vllm/transformers_utils/tokenizer_group.py,sha256=Zf_1tIiLgk_9HnIBJHEnuzRHBICJUBSiZFKB9u16tPk,5647
|
|
1216
|
+
vllm/transformers_utils/utils.py,sha256=C7fFp4Eyw5dGw9neyADzwExlhK5A0g0efIDVL3PHnzg,2699
|
|
1217
|
+
vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
|
|
1218
|
+
vllm/transformers_utils/chat_templates/registry.py,sha256=4zEDRuMLlYz_ihhLB1lvCNaF0cTwWZSQqNYOhikMEX8,2390
|
|
1219
|
+
vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
|
|
1220
|
+
vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
|
|
1221
|
+
vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
|
|
1222
|
+
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
|
|
1223
|
+
vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
|
|
1224
|
+
vllm/transformers_utils/chat_templates/template_minicpmv45.jinja,sha256=00aDdLodQQOp3g_FfnJOhCi5_PnVCgx9Vloo4CqDVqI,4295
|
|
1225
|
+
vllm/transformers_utils/configs/__init__.py,sha256=jdZ9Xauf30V6cS7veDk5U8uaRQPvbQ06AwQgxLREdWE,2401
|
|
1226
|
+
vllm/transformers_utils/configs/arctic.py,sha256=8WAZRegtPG1_qaFIplNemJJLlCLHBYB3p3m8ZR5co88,9053
|
|
1227
|
+
vllm/transformers_utils/configs/chatglm.py,sha256=TqBRltbV4V7NTnWe8a4nsrfBxXOqB0jBwjNiTkZtEPo,2941
|
|
1228
|
+
vllm/transformers_utils/configs/deepseek_vl2.py,sha256=BwZtrbgFNLRHyOu-yMpOS8uGIFamH8_DAWxw8RtzFJA,7296
|
|
1229
|
+
vllm/transformers_utils/configs/eagle.py,sha256=ZBCLYo90dTcEcs9U50SBnga_-2o0f6Z2OUPYKMfUcLE,3160
|
|
1230
|
+
vllm/transformers_utils/configs/falcon.py,sha256=vKXtykJL5NGzcDFfSnE532vBV5KLrQvOKm7v5P58y-Y,2986
|
|
1231
|
+
vllm/transformers_utils/configs/jais.py,sha256=1jEXh11bRdFpH8ptGPKOZaTOr-Ck_BCgMbXpc959eVg,10432
|
|
1232
|
+
vllm/transformers_utils/configs/kimi_vl.py,sha256=xXtkLgTdOt5ZgSxva36iLzgZqqklIoiHaoJhCNgJyVw,1486
|
|
1233
|
+
vllm/transformers_utils/configs/medusa.py,sha256=ZZcus4c6s4A1iTOPCR2bwzJpSHKsms98dycjVpmoi2E,2012
|
|
1234
|
+
vllm/transformers_utils/configs/midashenglm.py,sha256=JKW3CXlQTMlDkjD4lxiolBwxo9bL3Eep17VVSkZzan0,3665
|
|
1235
|
+
vllm/transformers_utils/configs/mistral.py,sha256=6siObSuQP6pRijQufGIL-ARbyCooOKg8gzkKlahTB_g,5751
|
|
1236
|
+
vllm/transformers_utils/configs/mlp_speculator.py,sha256=2it7HgAv-ZqGDLoE7q66oxXjk8R_mBdnGw31_TVXI7w,2500
|
|
1237
|
+
vllm/transformers_utils/configs/moonvit.py,sha256=Egyjh8mvpzPlX-RmbfDf8ZmeBe7K9fqimYX-QgK9NrQ,1272
|
|
1238
|
+
vllm/transformers_utils/configs/nemotron.py,sha256=ykEscgI_96g5NuKcHIfZQgfU03BX-K7k5MPwXBalJlY,9041
|
|
1239
|
+
vllm/transformers_utils/configs/nemotron_h.py,sha256=TQFOKLOEAJpgWcJp9wf88OvOGhJyIoE2fYHPNeFoIbg,12235
|
|
1240
|
+
vllm/transformers_utils/configs/nemotron_vl.py,sha256=pa78Qz3-ZVwzC_7NDP53CX26ef5iYQJxIaLCpvY_XHE,2151
|
|
1241
|
+
vllm/transformers_utils/configs/ovis.py,sha256=rd9b7wrJJ3PWN8e_1-6Wdvrvh0Z2tRy7ka_STa1MKck,7711
|
|
1242
|
+
vllm/transformers_utils/configs/qwen3_next.py,sha256=UVHJD5CkVcxhRKdc-GUhJ7OD1l63y9b25dbndxX_oPw,14666
|
|
1243
|
+
vllm/transformers_utils/configs/step3_vl.py,sha256=FCNUr1iCCw4si_VGfwA2fmAYmY_o2kr_J1qySNiFhGo,4500
|
|
1244
|
+
vllm/transformers_utils/configs/ultravox.py,sha256=Xkc7agFuZKcN3WR-qhFGpd03u6r7UsNJxTTPmv5VmUM,5166
|
|
1245
|
+
vllm/transformers_utils/configs/speculators/__init__.py,sha256=48Vcuw16i9R99vM3iDVkRkX107yJtFeTtdWgLQE-XFg,107
|
|
1246
|
+
vllm/transformers_utils/configs/speculators/algos.py,sha256=Zg1BJQ_ZeJPgEaNR_55xdggmd9TQUdZxuwenzvzoVOw,1057
|
|
1247
|
+
vllm/transformers_utils/configs/speculators/base.py,sha256=eoykwOJCpE34cK0ja9CpMCA2b5tWlVzVoBkX6qYSx4M,3712
|
|
1248
|
+
vllm/transformers_utils/processors/__init__.py,sha256=6-W37BhULZUjbu3aydrGxalPs4scPm2T7zzI6E86dik,644
|
|
1249
|
+
vllm/transformers_utils/processors/deepseek_vl2.py,sha256=pP0mV0mEatAjhT2V6VkXTmW7lDCiS8ilry8uD5sZdQg,14633
|
|
1250
|
+
vllm/transformers_utils/processors/ovis.py,sha256=DAzKptRfKcV7wGorJQxMIiZZ-rMMRtGKg-SEoyERUzM,18929
|
|
1251
|
+
vllm/transformers_utils/processors/ovis2_5.py,sha256=F-wW_Atb18w6fDV7t6VYz6X4PydU_jKaOzD41ygCbMI,19852
|
|
1252
|
+
vllm/transformers_utils/tokenizers/__init__.py,sha256=dN6RDCTGacE-3exN7VSZHlEcHhu__4dQM6Ry0lQ43w8,372
|
|
1253
|
+
vllm/transformers_utils/tokenizers/mistral.py,sha256=y0b3NYxiG6fFaPGGAP74xhfR_3EDO_a--QBKEF0hfnY,20613
|
|
1254
|
+
vllm/triton_utils/__init__.py,sha256=nYPnk0WE8v-eTi8lnnMXFWadX-uJkD8MuFLj9bFLEEE,543
|
|
1255
|
+
vllm/triton_utils/importing.py,sha256=L5Uv5_tQ1Esmqhg2ViNtCFav7IYEm0aI-Gacff6n0HE,3448
|
|
1256
|
+
vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1257
|
+
vllm/usage/usage_lib.py,sha256=qFy6_zSdBRAfeA4vdYFUDi5kDZqeY5o0Yaw4mjEHX-Y,9020
|
|
1258
|
+
vllm/utils/__init__.py,sha256=eX9p3oEF2zpf7-b7Tf2Jszd1iwooZUr-ot-eDc8JbYY,118053
|
|
1259
|
+
vllm/utils/deep_gemm.py,sha256=i1-CSD-FZjGJYt7YjYswbuHafveTUH3HBlDj45VP2-0,7185
|
|
1260
|
+
vllm/utils/flashinfer.py,sha256=WOMAFU1XwmpcugUC3oZET3amHGZzpJ34DTz01MZPU7w,12199
|
|
1261
|
+
vllm/utils/jsontree.py,sha256=c0jqNmvifnkRvpBH7_pbFdjL5j1BuZXUlkAeITALHoA,2384
|
|
1262
|
+
vllm/utils/tensor_schema.py,sha256=NktXc0qlmJH2MdHhVkOA1Jbb3KeB807_YcnYR1ZacJo,9290
|
|
1263
|
+
vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1264
|
+
vllm/v1/cudagraph_dispatcher.py,sha256=RZE3JXiwoyeokEJLKqc2CBSEQkELJeq-o7uMP66Q-S8,5894
|
|
1265
|
+
vllm/v1/kv_cache_interface.py,sha256=J07AHZIe83du8fyi3PDYRjR1BjPZbkeA23I2_LhOJcA,9876
|
|
1266
|
+
vllm/v1/outputs.py,sha256=eWrgVD9egqM1wSFEfLIiT04m8eQlNwVEwq6TMj8m05s,4541
|
|
1267
|
+
vllm/v1/request.py,sha256=pUmW9waAbcJV5zp7SZfePcxPAaNQPzJ_ai_24qdp7Qg,9009
|
|
1268
|
+
vllm/v1/serial_utils.py,sha256=bXKJ85USPtVp3kD6lOSSdt4uBHmQlBrWLaBETONE-7Y,16121
|
|
1269
|
+
vllm/v1/utils.py,sha256=7rXC9XC04zQVSaDlDHc35_9qvP39tF5Ib6SB5DcK6Qk,13227
|
|
1270
|
+
vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1271
|
+
vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1272
|
+
vllm/v1/attention/backends/cpu_attn.py,sha256=rSJVDTHYyankPPDGi-UbcGkWg02fyYmH5Tl5yqw2en4,34919
|
|
1273
|
+
vllm/v1/attention/backends/flash_attn.py,sha256=V1Z1PqzyPCWSQV4j5V-XPr06cA74UNVhXdhARF_bq34,33963
|
|
1274
|
+
vllm/v1/attention/backends/flashinfer.py,sha256=j8bVXWDPlApAZQMIy0-BNUMLgMan6BYwXxwva5V6Yu0,49503
|
|
1275
|
+
vllm/v1/attention/backends/flex_attention.py,sha256=pBpbu35uO2aP_UaGsYy-kt1H3yUJiqvlZ6nGkGQwZw0,31861
|
|
1276
|
+
vllm/v1/attention/backends/gdn_attn.py,sha256=0wxkZ4Rstnw0lcsW0MLw1FDfMmL_HpLChWwc3xVw6BM,14164
|
|
1277
|
+
vllm/v1/attention/backends/linear_attn.py,sha256=nLuobOVuEmZKIGNxG76bM-g5-Y-DyF5iIhWJ1rXG-So,2419
|
|
1278
|
+
vllm/v1/attention/backends/mamba1_attn.py,sha256=PVnvEFignF_JklZ9Zcdc15zHgGnys4Py3r_uCZkkdZI,3004
|
|
1279
|
+
vllm/v1/attention/backends/mamba2_attn.py,sha256=82UXdrkNyYKniD7g9-Q2J8ZyP8bxb7mrnP6iR9P4Gs8,9486
|
|
1280
|
+
vllm/v1/attention/backends/mamba_attn.py,sha256=6mI7pUA591oaJZTxXFMusz9c01LJkX8eRwXiNiUdvLw,1973
|
|
1281
|
+
vllm/v1/attention/backends/pallas.py,sha256=u7ek9fL2-ZmE1tR5Sye5c6K_UXJtW_m4Kuml74p4N_M,16162
|
|
1282
|
+
vllm/v1/attention/backends/rocm_aiter_fa.py,sha256=e_zXaNPquQXzRmmA9Y_kQM9c4OQunIM4L4e4n4Wd7n0,21229
|
|
1283
|
+
vllm/v1/attention/backends/short_conv_attn.py,sha256=2_9dCUPjE03FFNiZcBcdW20q8fkaxuWi5zjcgkElu8U,3025
|
|
1284
|
+
vllm/v1/attention/backends/tree_attn.py,sha256=stjsl_Knv0JCzZwAW4Ehsr9xR6sofjlteLvP_OQqK0Q,17059
|
|
1285
|
+
vllm/v1/attention/backends/triton_attn.py,sha256=4zwqw4f1x9PCbC7t8Eb47EavDT1RUXBQ-s9nQGQDAw4,17035
|
|
1286
|
+
vllm/v1/attention/backends/utils.py,sha256=M8IPcAOrS059jLTI6cm1IJbf-qqa3o1aTIDqsQQ4PIg,32833
|
|
1287
|
+
vllm/v1/attention/backends/xformers.py,sha256=cTILEVjNZxc1O2-ZQEWd2b62CW8SaIGsPBAC9smzJfY,16344
|
|
1288
|
+
vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1289
|
+
vllm/v1/attention/backends/mla/common.py,sha256=Oa0HEVdaN8g29ZhOuLgzjrJQ3CTRXUwtPAQw6JXulOs,66705
|
|
1290
|
+
vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=BerBrfftNSFyt74Vaqob61s8T5J5kM6Pfuht70Tgv7Y,11031
|
|
1291
|
+
vllm/v1/attention/backends/mla/flashattn_mla.py,sha256=bYh0vqUa04ZSKSXGophkvIaVw8x4vY_-ViOtPXHGKmk,11345
|
|
1292
|
+
vllm/v1/attention/backends/mla/flashinfer_mla.py,sha256=GsvyhXX_GzaU5E-WOwGRLSDpy7jSV8LZ-wnOm4bcJVs,3948
|
|
1293
|
+
vllm/v1/attention/backends/mla/flashmla.py,sha256=H6NK9-ZOmfthULRHDUmXl_XfCgjLtY_aVUMphZWxhdA,8520
|
|
1294
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=YuN73YmfH7Y080Qf_lu1--FRIFOdbjKtI_Zgre6gyf4,10387
|
|
1295
|
+
vllm/v1/attention/backends/mla/triton_mla.py,sha256=NO-syxy1Sl0XRHG1QPzZigqM3lTJIBe1mO5Uqz8lgIE,6505
|
|
1296
|
+
vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1297
|
+
vllm/v1/core/block_pool.py,sha256=ESLtgIYG4aJmmVETUFQXQBuqX6fEKvo3IxRGLDh5CHY,13319
|
|
1298
|
+
vllm/v1/core/encoder_cache_manager.py,sha256=ry0hrs7yJuMPLpQFhqNdi1egM_aS9xvANTLSPXHobrw,13578
|
|
1299
|
+
vllm/v1/core/kv_cache_coordinator.py,sha256=GSha9ADAUlsIVTiKemNREewBv3KKyrqbcvvXk-04stw,18764
|
|
1300
|
+
vllm/v1/core/kv_cache_manager.py,sha256=LkwVFY1Wnu_VIXAN4iDPmGziXsTilxhG6il39ElqfIM,16523
|
|
1301
|
+
vllm/v1/core/kv_cache_utils.py,sha256=xpzogRM8hZ8EHUTM3Iwd4cxrFqkfmG99oGDUdnGaE88,48703
|
|
1302
|
+
vllm/v1/core/single_type_kv_cache_manager.py,sha256=Wm9F_C0BzgHUMDjq4aMpuPl_ViJKROSOmDiu_rFxnG4,28703
|
|
1303
|
+
vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1304
|
+
vllm/v1/core/sched/async_scheduler.py,sha256=-YLUrdcsi2lQA6KnchxTH51Dge6CEpoUil5ECrJ4ltc,1771
|
|
1305
|
+
vllm/v1/core/sched/interface.py,sha256=igiz4ZBJhko2kZtj0iZaPwvNqqtoxammTTWLBxR4kMc,6102
|
|
1306
|
+
vllm/v1/core/sched/output.py,sha256=wMKi7Nd1g2_TyEuAcDhSSvRmGr_WfGFpKLuGQJ1fvWI,6022
|
|
1307
|
+
vllm/v1/core/sched/request_queue.py,sha256=c_fhiQL-oeOPVAoR_oKJppE2TjMRosabUDBQZgfbbI4,7533
|
|
1308
|
+
vllm/v1/core/sched/scheduler.py,sha256=K9KPwyzqcTcCmLuNoNmgu9FjqzFbLGQoVAEx45maJV8,60080
|
|
1309
|
+
vllm/v1/core/sched/utils.py,sha256=ysrETXRH9Pl3ZDb9-3fjtcu63_vA-8LVB-Jdbg4DDHE,2364
|
|
1310
|
+
vllm/v1/engine/__init__.py,sha256=B5WVQn_bsD464ylpsLAKXlkN_RHmUR9dnbg-VlLejqg,6021
|
|
1311
|
+
vllm/v1/engine/async_llm.py,sha256=diTW33jPIlJWAA2YmGmURAO5zvJSkm7ynzOmBMKljMs,30858
|
|
1312
|
+
vllm/v1/engine/coordinator.py,sha256=x60JQ_0GnhRvFMk1_A8_6ynglBv5JM4jFldc_mojcNE,16060
|
|
1313
|
+
vllm/v1/engine/core.py,sha256=0SGd4NUmsjJqRx_oRks7ilVzDcq2PqmeubFei5C7EWs,53999
|
|
1314
|
+
vllm/v1/engine/core_client.py,sha256=v4FcvCzOKGn3egjVOnRvQW8f1JX43Agfr2YOvi4SIYk,55182
|
|
1315
|
+
vllm/v1/engine/detokenizer.py,sha256=EYHWROcF0kyaNE1gBz11vO_2keoayIHJW4CVV2KrOMY,11512
|
|
1316
|
+
vllm/v1/engine/exceptions.py,sha256=OurXOSPqCuoLWzIZ2vi5ahe9NnyGESnO-HZqlvSB-Xs,731
|
|
1317
|
+
vllm/v1/engine/llm_engine.py,sha256=kJgjdjcyB0tcQhs2WO2WzRtmWa9MNPgZaFZ9F3NnC7U,13235
|
|
1318
|
+
vllm/v1/engine/logprobs.py,sha256=lEStN84KAzoy8JPbmxEeuPuoUwBz1zRRSmeg4JMy4cw,7242
|
|
1319
|
+
vllm/v1/engine/output_processor.py,sha256=UPXgql0Lfs4IZjLebjc3bb66ChwNLyL5W2dZGJ524E0,22807
|
|
1320
|
+
vllm/v1/engine/parallel_sampling.py,sha256=uViFaH5NFxMQfWBz8rOdRZ5eIb_ZHMlJu3aCuhq2TIM,4834
|
|
1321
|
+
vllm/v1/engine/processor.py,sha256=NuYUt0vq6vkzNQlsL75c-vz-TIECuEOGnaqWeY9DS50,22925
|
|
1322
|
+
vllm/v1/engine/utils.py,sha256=5PDA_rrt6OM0ZtyRDppwAktDiIN2nmPUqvg880YsYho,34896
|
|
1323
|
+
vllm/v1/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1324
|
+
vllm/v1/executor/abstract.py,sha256=ypF4zlL4bQiZMV4YwjqY8TXlsUW1zfztxOybvCIRvZ8,5190
|
|
1325
|
+
vllm/v1/executor/multiproc_executor.py,sha256=UGPO0EeVetZOupd08k27GLNBpX6dEYB1CGAITs08eE4,27341
|
|
1326
|
+
vllm/v1/executor/ray_distributed_executor.py,sha256=3CFQ9Z0Z_dJPmIHhUuS7BnuN3miVnDWa31sGE4qKNEk,4117
|
|
1327
|
+
vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1328
|
+
vllm/v1/metrics/loggers.py,sha256=JkRQnF627-Iu1acs8L7oYAWZhkjt5MtJlkwbiNbfc9g,30683
|
|
1329
|
+
vllm/v1/metrics/prometheus.py,sha256=7OX8teYEAtWHc0w2I61fhm6RZ5zYTIzsxj_5SZYUAMY,2842
|
|
1330
|
+
vllm/v1/metrics/ray_wrappers.py,sha256=ju4Bb7bMhrotlr4_xqB6HpVpsUhD4Vd8u5kMPhkbyKg,4627
|
|
1331
|
+
vllm/v1/metrics/reader.py,sha256=9rx29TV3t8P49Hx4a_F1LB2WHTwFDHkVc5v3utoEOFg,8702
|
|
1332
|
+
vllm/v1/metrics/stats.py,sha256=QjtXnpc2o6L23SWr-ah53YkvMs4yMU0jRS8dpljiVkw,9669
|
|
1333
|
+
vllm/v1/pool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1334
|
+
vllm/v1/pool/metadata.py,sha256=uTC6kmLYY0FS8VACsdxgO5XOr-VR5GZq-P3hzjXqkg8,2919
|
|
1335
|
+
vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1336
|
+
vllm/v1/sample/metadata.py,sha256=H6Wj5GnL_vxFqq__NMYoTM2BEFb2fnsHBpuJ42D8wiM,1110
|
|
1337
|
+
vllm/v1/sample/rejection_sampler.py,sha256=bJtj8LeJpOWzTKCv8C86ljjRQodqnfyFaPYbg-5AhVs,22732
|
|
1338
|
+
vllm/v1/sample/sampler.py,sha256=We8PDdxn2DaZdUb74_wix1mwZhgoGD-F863jG2wwXKA,11222
|
|
1339
|
+
vllm/v1/sample/logits_processor/__init__.py,sha256=bV65an0m9TGTrJGr1YGzz32XecZbOV1K8sLBP4snspU,10925
|
|
1340
|
+
vllm/v1/sample/logits_processor/builtin.py,sha256=kkueDUJgSGh15Q890DY2N2njvGCHcIqjNOhKmWCigbQ,11028
|
|
1341
|
+
vllm/v1/sample/logits_processor/interface.py,sha256=O1sU995BNa9yTvd_-yvQ_1q65v2MOdwbXYIU3sTNknU,2994
|
|
1342
|
+
vllm/v1/sample/logits_processor/state.py,sha256=p9hEr16WYUiI82dW-mTR9kib89ldXsIyluT5QrvM6Lw,5819
|
|
1343
|
+
vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1344
|
+
vllm/v1/sample/ops/bad_words.py,sha256=JOnrJXq2RD45cA7cmePX2ktRjBg_1uJQsPqCc0gf2Vw,1191
|
|
1345
|
+
vllm/v1/sample/ops/logprobs.py,sha256=E5pKlavblNL2n9CNhodL34_F4iAVaXA4f6SfRSWzd9w,973
|
|
1346
|
+
vllm/v1/sample/ops/penalties.py,sha256=B3IZcrvPBxl2jzTVYlIh3Ty2VSI5y4CD6he1B3Nlkx8,1534
|
|
1347
|
+
vllm/v1/sample/ops/topk_topp_sampler.py,sha256=NQTY0R6iSzXMqUN5A5MPMVEID7UUz9zMUjp3_4ucYgo,10135
|
|
1348
|
+
vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1349
|
+
vllm/v1/sample/tpu/metadata.py,sha256=4UVHpx8QO2lNOnMON7ZY9oSfVzhjRemOa0_w3C05OeI,4695
|
|
1350
|
+
vllm/v1/sample/tpu/sampler.py,sha256=wQnkNmxnZn6vIY1PMSL2CQwYeOWd2eF-IWTLjjWcyH4,7702
|
|
1351
|
+
vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1352
|
+
vllm/v1/spec_decode/eagle.py,sha256=b7tUtFFZcB9SH3jmuIpGFH9DEaw64WrFT12YFBoZ7UI,34205
|
|
1353
|
+
vllm/v1/spec_decode/medusa.py,sha256=DPD5dD500vUaR4l6r46fjrmwkvDAyfNRq3UOHd7k53g,2365
|
|
1354
|
+
vllm/v1/spec_decode/metadata.py,sha256=I3rD5wVyLs5ID9LnIN3E5hy0lu5Eetz5DGcxstQMeR0,2257
|
|
1355
|
+
vllm/v1/spec_decode/metrics.py,sha256=gv7p69_ZMrSOtQ7TOxJPUuUInpVkyctDHuIqIzFdf5Q,7245
|
|
1356
|
+
vllm/v1/spec_decode/ngram_proposer.py,sha256=8GLSbNLKNcI81y4c3K22CGECfMbrzDAV5OW0COcA7rc,6174
|
|
1357
|
+
vllm/v1/spec_decode/utils.py,sha256=EgqNXyhwHkoaxklEttaN4sPh53LVXcpstD1T0yjjnos,591
|
|
1358
|
+
vllm/v1/structured_output/__init__.py,sha256=9sG8kR_vUfmBOcqqAzh6JTWmipFzy4zJqW84wCKMWtM,13036
|
|
1359
|
+
vllm/v1/structured_output/backend_guidance.py,sha256=X_5Ajlp2t1twy10Oit1OVU3t4pWQelu5Q-N8JXOTzpc,8784
|
|
1360
|
+
vllm/v1/structured_output/backend_lm_format_enforcer.py,sha256=bSgZWtfYQhWwCdj_848ZyNuGjTGIZbUJjpampdEXv3M,6421
|
|
1361
|
+
vllm/v1/structured_output/backend_outlines.py,sha256=kZ3YWvblpUQpKphljxALwOIXJLGF4SI4QVcoH5DyBYg,12208
|
|
1362
|
+
vllm/v1/structured_output/backend_types.py,sha256=WSSoKU5aqW2CkRVJ4AKRUpFbMLbei1-U1jS7ioITEsA,3810
|
|
1363
|
+
vllm/v1/structured_output/backend_xgrammar.py,sha256=LcA0nHMGZV0WHATHA2rd2h4rWdqKx0e6J9nzHJVGVGw,12487
|
|
1364
|
+
vllm/v1/structured_output/request.py,sha256=qEeKTd0vL27BJ4cPvnlF8O9bVzfALoxekG-fNA3Sr8o,3220
|
|
1365
|
+
vllm/v1/structured_output/utils.py,sha256=2lT103Hk9EqyoLWMDn-_hmnXFqRTrGeoi_Gtf_41nM0,13058
|
|
1366
|
+
vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1367
|
+
vllm/v1/worker/block_table.py,sha256=ycY6lXeZibNCin9SlcRjEiDSRdkDcGSRFU46Ut7-oaY,8985
|
|
1368
|
+
vllm/v1/worker/cpu_model_runner.py,sha256=FB86wXtkwD6-7xYWe701FKWInUsdIfmFC0ozl_FGsb0,6197
|
|
1369
|
+
vllm/v1/worker/cpu_worker.py,sha256=-Po6EYl1PKYywLghCEDRlun09_SiNyXEs99axHJg9os,7950
|
|
1370
|
+
vllm/v1/worker/gpu_input_batch.py,sha256=8UMoYCBqxCgrxZdksnlm7fGw4EuceWUFP6VWWJUKEIw,35861
|
|
1371
|
+
vllm/v1/worker/gpu_model_runner.py,sha256=gYwl60np3BJRxjCEWiVQSWElfxRYUfdI7ksuqYDthjw,173056
|
|
1372
|
+
vllm/v1/worker/gpu_worker.py,sha256=ilDHxjPqX54UNgAp4VUZKZdakc2qdQ3ivjrpkivbH18,31316
|
|
1373
|
+
vllm/v1/worker/kv_connector_model_runner_mixin.py,sha256=6Cr87LIGxouCN6d4lPc7vQmwmHbb57UEx5vV2rt4d0c,5022
|
|
1374
|
+
vllm/v1/worker/lora_model_runner_mixin.py,sha256=Fpmrof3lSxHrehmgt3uO4rsK2loD2WUtg0F3ohGSCjg,7505
|
|
1375
|
+
vllm/v1/worker/tpu_input_batch.py,sha256=cMdio9ZPbeWDAMCTuzi1x5mOoVFhBSkayoDZY1vt5W4,26015
|
|
1376
|
+
vllm/v1/worker/tpu_model_runner.py,sha256=DWSU5e3FYGu8qwM1ql7h3zSf7rzpridjlHtB71qb7Hs,91628
|
|
1377
|
+
vllm/v1/worker/tpu_worker.py,sha256=grHkrjC3hJLu8WgDpQOPLm-ojDuP7kXPBEYZYgMUeFM,14588
|
|
1378
|
+
vllm/v1/worker/utils.py,sha256=IxC2EKUMntwbEZ5TT4nCODaovqs3zMmEfXmbwsfqGI4,10899
|
|
1379
|
+
vllm/v1/worker/worker_base.py,sha256=X-XvcP0lzixzgizEv9p4yn2m9Fex4Efl39OlOuFg8A4,2048
|
|
1380
|
+
vllm/v1/worker/xpu_model_runner.py,sha256=abXuK4O7GG7_rCTIeGJBn5iYZZap8JcDHodZw7X_0j0,1351
|
|
1381
|
+
vllm/v1/worker/xpu_worker.py,sha256=Rli9bmjJdk81qmF5PVfLl21onWsnHVKP_RJfqIEAmDI,8151
|
|
1382
|
+
vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1383
|
+
vllm/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1384
|
+
vllm/worker/cache_engine.py,sha256=CsyWo93EoS2h6VKrn-LfgGMlEq_X8B5Mu4j_og6qhaY,6075
|
|
1385
|
+
vllm/worker/enc_dec_model_runner.py,sha256=07KUdhrsEwh9Xny_fem2-93ysXq8-1MBx1fFq1T58sA,23986
|
|
1386
|
+
vllm/worker/model_runner.py,sha256=FVInHZL7AgRxyTtHQr_My97eoCKbdSNtMQ71ldvkGjo,89928
|
|
1387
|
+
vllm/worker/model_runner_base.py,sha256=QacLHo40f31hPezcpYUAhzG336Jd5y9QGov2Ey2MzRY,10291
|
|
1388
|
+
vllm/worker/utils.py,sha256=jBGTDB35L79L2kDiQI1le4uFcxfFQj-yTNSJ9eDoQKE,1809
|
|
1389
|
+
vllm/worker/worker.py,sha256=DbRO2XVRVkJENhecFywciTxizshnm382G7h9HIzm-1o,30501
|
|
1390
|
+
vllm/worker/worker_base.py,sha256=07uhLbZCfKIm82FYa2KakXyiX9jWnzpIMw6zYhqiZbo,26195
|
|
1391
|
+
vllm_cpu_avx512vnni-0.10.2.post2.dist-info/METADATA,sha256=a8DB5DYqRvqOKclx-EO3Io-Il-gXHOqeDNMLgO7NvN8,15807
|
|
1392
|
+
vllm_cpu_avx512vnni-0.10.2.post2.dist-info/WHEEL,sha256=IoFti0xAvoDtAxuPJyI4RJkGn0ThylEbxytRcNSoLaU,113
|
|
1393
|
+
vllm_cpu_avx512vnni-0.10.2.post2.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
|
|
1394
|
+
vllm_cpu_avx512vnni-0.10.2.post2.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
|
|
1395
|
+
vllm_cpu_avx512vnni-0.10.2.post2.dist-info/RECORD,,
|